Project Overview We are building an AI-powered voice receptionist agent for a dental practice client. The agent will handle inbound calls 24/7 — booking, rescheduling, and canceling appointments, answering FAQs, and escalating complex situations to a human. The voice layer is built in Retell.ai and the orchestration/automation flows run in n8n, with integration into a dental practice management systems. This is a hands-on build role, not consulting. You will design, configure, and iterate the agent working directly with our founding team. What You'll Build: Conversational voice flows for new and returning patients (booking, rescheduling, cancellations, FAQs, insurance questions, urgent/emergency triage) Clean escalation paths to human staff when the agent can't handle the call n8n workflows connecting the voice agent to the practice management API for real-time schedule reads/writes HIPAA-conscious configurations and tool choices throughout the stack Performance tracking and iterative prompt/flow improvements based on real call feedback Seeking an Expert Who: You've built multiple production voice agents, ideally in healthcare or dental, and can own the full stack from architecture to delivery. You think critically about latency, barge-in behavior, edge cases, and HIPAA compliance — not just happy-path flows. Requirements: Deep expertise in Retell.ai — prompt tuning, latency optimization, interruption/barge-in handling, LLM selection, and cost modeling Advanced n8n automation — complex branching logic, dynamic data handling, external API integrations, and error recovery Experience with dental or healthcare organizations — you understand how practices operate, what front desks actually deal with, and how to translate that into agent logic HIPAA awareness — you know which tools and configurations are appropriate for PHI workflows Track record of full-cycle delivery: scoping → build → pilot → iteration Nice to have: Dentrix Ascend integration, NexHealth, prior AI receptionist or appointment-booking agent for a clinic/practice. 📋 To Apply, Please Answer Have you built a production voice agent with Retell.ai? If yes, briefly describe it. What's your approach to managing Retell.ai per-minute costs on an inbound call agent? Have you worked with dental or healthcare clients before? What was the workflow? Paste a relevant n8n workflow screenshot or describe your most complex flow.

I have built out an MVP using lovable for the wedding content creator community. It is a gallery platform where they upload their iphone videos and it displays in a gallery (Like pic-time, pixieset, etc). Our users primarily record 4k short form iphone videos and the upload pipeline is the most important piece. I dont have background in any of this and have only build with lovable, but the business is growing quickly and I would love some help to fix bugs and harden the pipelines/overall architecture. We use Cloudflare, Backblaze, Mux, Fly, and Lovable. We haave also built out an app that is on Testflight (Primarily what our users are using to upload).

Long-term partnership. Individual operator or tight team. Bootstrapped venture. Propose your engagement. Project Overview BuildQuest is a SaaS marketplace helping homeowners plan $100K–$2M construction projects — major remodels, additions, custom builds. We solve a chronic problem that has plagued residential construction for decades, and we solve it from both sides of the marketplace. Order matters: BuildQuest was built to serve homeowners first. Pros come second. That orientation defines our positioning, pricing, and every decision. What we are BuildQuest is a real SaaS platform in active development — not a slide deck and not a solo founder side project. There’s a serious engineering team, a UI/UX and product lead, and an advisory board with deep tech backgrounds. The product is in good hands. What’s been founder-built and now needs a marketing partner is the public-facing marketing layer — brand voice, story, creative, distribution, infrastructure. That’s the work this hire takes over. Companion Document We’ve also attached the BuildQuest Marketing Manifesto to this posting — eight specific beliefs that shape what we’re hiring for. Please review it before responding. Candidates who reference it directly in their proposal will be evaluated more favorably. The two-sided problem Homeowner side (B2C — primary audience, paying customer). Planning a major project today means fragmenting effort across Pinterest, contractor calls, cost calculators, and trial-and-error research — to figure out what to build, articulate a personal style, land on a realistic budget, and find qualified pros. Months or years. Many projects die in the planning phase. Pro side (B2B — served through serving homeowners). Design and construction pros burn hundreds of hours on unrealistic prospects, then get charged by referral services to chase the same kind of leads. They’re tired of being courted as the customer. How BuildQuest flips the script. Most marketplaces in this category court pros as the customer and treat homeowners as the lead being sold. We do the opposite. Homeowners are the paying customer. Pros earn access by being good at their work — and what they get is fundamentally different from a referral platform: clients with clear scope, defined style, realistic budgets, ready to engage. That’s the B2B strategy: serve pros by serving the homeowner well. Why Now • AI is rewriting consumer discovery. Google search volume is plateauing for the first time. Homeowners increasingly ask ChatGPT, Perplexity, and Claude. The search-and-aggregator model that built Houzz and Angi is structurally shifting. • The referral-platform model is collapsing under pro fatigue and broken unit economics. • Consumer expectations for premium service in residential construction are at an all-time high — with almost nothing in the current landscape meeting them. Someone builds the homeowner-first incumbent in this space within the next 24 months. We intend it to be us. The marketing partner who joins now helps decide what that brand becomes. Why this engagement is different Long-term partnership, preserves your independence. Joining for the long haul — not executing a campaign and disappearing, and not a soft pitch to W-2. The best independents are independent for real reasons; we respect that. Brand DNA, not brand amplification. The narrative, voice, message architecture, and launch playbook are still being shaped. You help architect them. That window closes at launch. A storytelling and visual craft role at its core. The marketing partner owns the brand’s words and the visual output of marketing — mockups, ad creative, collateral, video concepts, social. Clint runs UI/UX and product design; the marketing partner runs marketing design. Two crafts, side by side. Founder-led content is the engine. Bill’s podcast (59 episodes and growing), book, and 30+ years of expertise are the engine. The partner builds the systems around it that scale the founder’s authority — amplification, distribution, repurposing. Founder-engaged collaboration. Bill is present at the weekly working session, looped in on meaningful decisions, and reviewing what goes out before it ships. The partner brings finished thinking and finished work; Bill reacts, we refine, we ship. Decisions happen in days, not months. Core focus areas Creative voice, copy & visual execution (primary) • Develop the brand voice and message architecture for both audiences (homeowner-first B2C, pro-serving B2B) • Write the core marketing collateral — landing pages, email sequences, ad copy, sales pages, social posts, video scripts, podcast descriptions • Produce designed mockups and finished-feeling marketing collateral — show up to working sessions with visualized concepts, not just briefs • Identify hook points — the moments where a homeowner (or pro) commits — and architect messaging and creative around them • Build the educational content strategy that translates 30+ years of construction expertise into content that genuinely teaches and converts • Develop launch narratives across pre-launch, beta, soft launch, public phases Launch & lifecycle systems (primary) • Design and execute waitlist and beta tester recruitment • Recruit design and construction pros to the platform’s free tier • Architect the full lifecycle — acquisition, activation, retention, expansion, referral, win-back • Run early acquisition tests with discipline on owned vs. rented attention Distribution & owned channels • Build distribution systems that turn content into actual attention • Prioritize owned media (email, podcast, community) over rented (paid) • Establish partnership and co-marketing strategy with adjacent brands Polish & revamp the marketing layer • Elevate the current marketing websites (founder-built; in need of partner-driven polish or revamp) • Audit and elevate current social presence and email list • Keep / optimize / rebuild decisions; lead execution Marketing infrastructure • Propose and implement CRM, automation, analytics, reporting • Email automation workflows • AI-augmented content workflows turning 59+ podcast episodes into multi-channel reach Content strategy, SEO & AI-era discovery • Modern SEO: semantic search, topic clusters, E-E-A-T • AI-era discovery: GEO/AEO, structured content for LLM citation, presence inside AI-generated answers • Repurposing systems for long-form expertise • Local SEO for the pro side Required capabilities Creative voice and copy. This role lives or dies on storytelling. You take 30+ years of construction expertise and turn it into stories homeowners feel and pros trust. You write hooks that convert. You design educational content that earns trust by genuinely teaching. You think in hook points and architect messaging around them. You write in long-form and short-form, B2C and B2B. Visual design fluency. You bring concepts to life visually — mockups, layouts, ad creative, social posts, video concepts, marketing collateral that’s already designed when it hits the table. Fluent in modern design tools (Figma, Canva, AI design and video tools). You produce finished-feeling work without waiting on a designer. Sector experience. U.S. home improvement, real estate, or residential design/construction — or proven ability to go deep on a complex category fast, with portfolio evidence. 0→1 launch experience. You’ve shaped brand positioning from scratch and taken products through pre-launch → beta → soft → public launch. Portfolio work to show. AI-era discovery (GEO/AEO). You build for presence inside AI-generated answers, not just search results pages. The most consequential shift in marketing discovery since Google itself The mission for a 2026 launch. Distribution-first thinking. Content abundance is no longer the constraint; distribution is. You measure success on reach and engagement, not output volume. Lifecycle marketing. You think in the full arc — acquisition, activation, retention, expansion, referral, win-back — not just the funnel top. Modern, AI-augmented marketing practice. You’ve built technology-augmented workflows that deliver meaningful productivity gains. Show us how a single operator or tight team uses today’s tools to deliver what used to take ten people — and how that leverage serves both sides of a two-sided marketplace. Analytics, stack architecture, systems thinking. Expert-level analytics, A/B testing, attribution, dashboard design. Can propose and implement a marketing stack appropriate to an early-stage two-sided SaaS. Reusable workflows. Strongly preferred • Two-sided marketplace experience — chicken-and-egg dynamics, geographic clustering, network effects • Vertical SaaS marketing — deep industry credibility, partnerships, community over feature comparisons • Founder-led content systems — you’ve built repurposing and distribution around a founder’s voice without losing the voice Helpful, not required • Performance marketing (Meta Ads, Google Ads, LinkedIn) • Podcast and long-form content optimization • Conversion rate optimization • Prior fractional or agency experience with early-stage clients What you’d be working with • Podcast: 59 episodes (and growing) of long-form expert content with established production workflows • Quinn AI Guide: designed character with voice synthesis and locked tagline, integrated into the platform • Companion brand: book + podcast feeding the platform’s AI knowledge base • Brand Standards v2: visual identity foundation in place • Two marketing websites — founder-built; in need of partner-driven polish or revamp • Live interactive tools on the platform site (proof of the platform philosophy) • Social presence across multiple channels — also founder-built, also needs elevation • Small email list ready to grow and segment How the founder works High standards, intense attention to detail. Every element of design, development, and brand reflects 30+ years of working on projects where one missed detail costs months and tens of thousands. Founder-engaged collaboration. Bill is present at the weekly working session, looped in on meaningful decisions, and reviewing what goes out before it ships. The partner brings finished thinking and finished work; Bill reacts, we refine, we ship. Decisions happen in days, not months. Deep respect for marketing’s value. Bill is not the founder who treats marketing as “spend” or expects magic. He’s looking for a partner whose expertise he respects, whose work he’ll back, and whose voice carries weight in decisions. Dual-vantage perspective. Bill operates from rare understanding of both homeowner and pro perspectives. Expect this to enrich every conversation about positioning, message, and audience. Engagement Structure We are intentionally not specifying fixed hours, retainer amounts, fee structures, or budget. We want you to propose what fits this engagement. Tell us: • Solo operator or tight team • Time commitment you’d propose for this scope • Engagement model (retainer, project-based, hybrid) • Marketing stack you’d recommend and approximate run-rate cost • How you’d structure the first 90 days • Your view on staying beyond launch as a long-term partner We evaluate on quality of thinking, fit with our reality, and the strength of the work itself — not just on price. Application Requirements Please submit your proposal through Upwork with the following: 1. Respond to the Manifesto Review the BuildQuest Marketing Manifesto (attached to this posting). In your cover letter, name 1–2 principles that most resonate with you and 1 you’d push back on or refine. This isn’t a trick — we want genuine engagement with how we think. 2. Cover Letter (300 words max) • Your reaction to the Manifesto • Your sector experience — home improvement, real estate, residential design/construction, or how you’ve gone deep on complex categories before • How you operate as a modern, AI-augmented marketer — and how that leverage serves both sides of a two-sided marketplace • Your view on long-term partner vs. project-only work 3. Writing Sample One piece of writing you’re proud of — a landing page, email sequence, long-form post, ad campaign, or brand narrative. The piece that best represents your voice and your craft. Attach it directly, or describe it in your proposal with a clear summary. 4. Visual Sample One piece of marketing design work you’ve produced — ad creative, social, landing page mockup, video frame, or marketing collateral. Attach it directly, or describe it clearly. We want to see your voice and your visual craft. 5. Portfolio (2–3 examples) • A 0→1 brand or launch you’ve shaped from scratch • A modern marketing workflow or system you’ve built — using technology including AI tools as force multipliers • A messaging architecture or positioning framework you’ve developed • Bonus: home improvement, real estate, marketplace, ConTech/PropTech, or founder-led content systems 6. Stack & Approach • The marketing stack you’d propose for an early-stage two-sided SaaS (homeowner-first) • Your view on AI-era discovery (GEO/AEO) and how you’d execute on it • Your default tools and why — especially CRM, automation, content, analytics • Approximate monthly run-rate cost of the stack you’d propose 7. Engagement Proposal • Solo or tight team • Time commitment • Model (retainer, project, hybrid) • Indicative fee structure • 90-day approach at a high level • Long-term partnership perspective 8. Three References • Preferably from B2B/B2C SaaS engagements • At least one able to speak to modern, AI-augmented capabilities Optional but valued • Short Loom video (2–3 minutes) introducing yourself • Example of a workflow or automation you’ve shipped Interview Process • Initial call with the founder (30 min) — fit, background, sector experience, Manifesto reaction • Take-home exercise (finalists only) — brand audit, positioning hypothesis, 90-day approach, stack recommendation, AI-era discovery move, and a 200-word creative sample • Working session with founder + designer (90 min) — present the exercise, discuss thinking, share visual samples • Reference checks • Final negotiation on engagement terms and offer About the Founder 30+ years in residential design and construction. Author of a published book on the homeowner experience. Host of a long-running industry podcast (59 episodes and growing). Advisory board includes past clients from Apple and senior tech leadership roles. Has built the AI guide and content workflows powering the platform — which is part of why he thinks differently about what a small team can do with modern tools. Mission: Serve homeowners first. Solve a chronic, decades-old problem at the front of the residential construction value chain. Deliver pros a fundamentally different kind of client — by serving the homeowner well.

We are looking for an expert backend developer and automation engineer to extend an existing, production-grade Model Context Protocol (MCP) server and overhaul its orchestration layer. The headline correction for this project: the existing Lawfather MCP is to be retained and extended, not rebuilt. It already exposes deterministic, parameterized Playwright tools for every required county portal (District Clerk, HCSO, HCDAO) and a client database. Those backend tools are the reliable layer and are not the source of the instability this project exists to fix. The instability lives entirely in the orchestration layer — the model-driven layer that decides when and how to call the tools. The fix is to move deterministic control out of model-followed prose and into code, and to host the agent on an always-on machine with persistent memory. Core Project Principles • Extend, Don't Rebuild: Retain and extend the existing MCP; do not re-implement portal scrapers from scratch. • Code Over Prompts: Deterministic logic lives strictly in tool code, never in instructions the model must remember each session. • No Caller Loops: Batch operations must run to completion server-side. No operation may require the caller (model) to loop. • Agnostic Architecture: The system must remain model-agnostic and host-agnostic. No single provider — Anthropic, OpenAI, Z.ai/GLM, or Nous — may be a hard dependency. • Privilege First: Client data stays on owned hardware; the model is never the gatekeeper of which case a file belongs to. Existing Tool Inventory (To Be Inherited As-Is) The following tools already exist on the production MCP (containerized on a local Synology NAS) and are in daily use. Re-deriving their behavior is completely out of scope: • hcdc_get_docket: Court settings by date range + bar number (District Clerk). • hcdc_check_filings: Per case: standard defense filings present vs. missing. • hcdc_download_filings: Images-tab documents: bulk OR selective by filters; dest_subfolder; dry_run. Note: The parameterized download tools already cover most retrieval requests. "All filings," "this filing," "all subpoenas," "all resets," and "everything filed that day" are argument combinations on this tool, not separate features. • hcso_locate: Defendant custody location (facility / floor / pod) by SPN. • hcdao_grab_file: Download a single named file from the DA portal Files tab. • hcdao_download_discovery: Batch / delta discovery download from the DA portal. • hcdao_download_media_alert: Batch-download files listed in a 'New Media Available' portal email. • hcdao_case_summary: Scrape the Case Jacket quick summary / DAO narrative. • hcdao_plea_offer: Scrape current plea offer + full offer history. • hcdao_assigned_ada: Assigned ADA name / email / phone on a case. • lookup_client / list_clients: Resolve / list clients from the shared client database. Scoped Work (Paid Deliverables) 1. County Case Resolver (New Tool): Find a case from partial identifiers — any subset of (name, SPN, DOB, court, cause). Searches county systems (not just the local client DB). MUST return a ranked candidate list for the user to choose from; MUST NEVER auto-select. Wrong-defendant selection is a privilege failure, not a cosmetic bug. 2. Latest-Version Retrieval: Add scope=latest to hcdao_grab_file so 'most recent' selects the newest among supplements instead of the first match. 3. Async Transcribe Tool (Skill to Tool Promotion): Build a deterministic MCP tool using Gemini 3.1 Pro Preview for transcription, followed by a second pass that sends the transcript back with case context for cleanup (speaker mapping, defense-moment preamble). Long-running: implement as an async job (submit to job id to poll to fetch), NOT a synchronous call. 4. OCR Tool (Skill to Tool Promotion): Implement a readability check on ingest. If a document is not cleanly readable, FLAG it and ASK before sending to Gemini 3.1 Pro Preview for OCR. OCR must be gated and confirmed, never automatic. 5. Server-Side Batch Jobs: Move all chunk, loop, delta, and throttle logic OFF the caller and INTO the tool code. One call runs the batch to completion. 6. Queued HCDAO Fixes: For hcdao_download_discovery, add a portal_ids filter for targeted single-file pulls and a custom output-path / Drive-folder destination feature. Known Portal Quirks to Handle from Day One • hcdc_get_docket returns a broader date range than requested; results must be filtered to the requested window. • hcdao_download_discovery delta detection is blind to files organized into dated subfolders and must be explicitly handled. • Court DG7 does not surface through standard bar-number docket lookup and requires separate handling. • The Playwright Node.js driver subprocess can die silently while database tools respond; you must health-check the driver proactively. Orchestration, Host Layer, & Deployment Topology • Target Host: Hermes Agent (Nous Research) running as the persistent shell, providing persistent memory, the scheduler, and messaging surfaces. The MCP server will plug directly into it. • Agnostic LLM Routing: Default the agent/dispatch role to the most reliable tool-calling model (currently Claude Opus). Route bulk, non-critical generations (draft summaries, transcript cleanup) to a cheaper model (e.g., GLM-5.2). No provider may be hard-wired. Per-tool pins are allowed strictly for transcription/OCR tasks (pinned to Gemini 3.1 Pro Preview). • Memory Fencing: Hermes's persistent memory and learning loops must remain enabled to accumulate facts and user preferences. However, the agent must be strictly fenced from self-editing or rewriting its own mechanical execution paths (portals, downloads, filings), which must remain frozen in MCP tool code. • Hardware Deployment Infrastructure: • Always-on Brain: M1 Pro MacBook Pro (16 GB, mains-powered, lid open) running the Hermes gateway, Messages.app, and a BlueBubbles iMessage bridge. Must be fully automated via launchd services to handle headless crash recovery, auto-login, and sleep prevention (pmset autorestart / caffeinate). • Tools and Storage: Synology NAS (10.0.0.149) hosting the Lawfather MCP container, local client folders, and Drive sync. • Private Network: Tailscale mesh across all devices for secure remote access without open inbound ports. Acceptance Criteria for Sign-Off • No batch operation requires the caller to iterate. • The case resolver returns ranked candidates and never auto-selects. • Transcription runs seamlessly as an async two-stage job surviving multi-hour files without timing out. • OCR never fires automatically on low-readability files without gated confirmation. • Zero regressions on the existing MCP tool inventory. • The Resiliency Test: The full stack successfully restarts completely unattended after a host reboot or simulated power loss, and is reachable via iMessage/SMS immediately after. • Self-editing is fenced on mechanical download/filing paths. Hard Guardrails • Privilege: Downloads route strictly to the correct client folder; a wrong-case match is treated as a severe defect, not a warning. Privileged audio/discovery data stays on owned hardware where the chosen model allows. • Determinism: Repeatable steps live entirely in tool code, never in prompts. • Agnosticism: Model and host layers must remain fully swappable without modifying the core MCP tools. Before quoting "done," you will be expected to confirm live portal behaviors regarding District Clerk document labels, DA portal stable identifiers, and county search surfaces. How to Apply Please submit a proposal detailing your specific experience with MCP architectures, Playwright browser automation, and macOS/Docker DevOps automation. Anti-Bot Filtering: To prove you read this entire scope, please start your application with the phrase "PROTECT THE LAW" in all caps. Automated or generic copy-paste applications will be instantly rejected.

Senior SEO Specialist Creative Heights | Remote Contract via Upwork About Creative Heights Creative Heights is a digital agency that builds, markets, and supports websites for a roster of growing businesses across multiple industries — including online education, home services, real estate operations, adventure travel, industrial manufacturing, and leadership training. Our work spans WordPress and WooCommerce development, paid advertising, content production, and full-stack marketing strategy. We're looking for a senior SEO Specialist to join our team as a long-term contractor and own SEO strategy and execution across our client accounts. The Role This is not an entry-level position and it is not a list-builder gig. We need someone who can walk into a client account, audit what's broken, build a prioritized roadmap, execute on it, and report results in plain language. You'll work directly with our team and occasionally with clients, so clarity and ownership matter as much as technical skill. You'll be SEO lead across 5–7 active client accounts, with workload split between technical SEO, on-page optimization, content strategy, link building, and — critically — Generative Engine Optimization (GEO) for AI search products like ChatGPT, Perplexity, Google AI Overviews, and Claude. We are looking for someone who knows how to do things and has actually done things. Theory is cheap. We want a practitioner who has shipped work and gotten measurable results. We will ask for specific references and we will call them to verify. What You'll Do • Generative Engine Optimization (GEO) / AI Search. Get our clients cited, surfaced, and recommended inside ChatGPT, Perplexity, Google AI Overviews, Claude, and other AI search products. You should have a clear strategy and a playbook you can implement from day one — not a thesis on what GEO might become, but a working approach with proof it moves the needle. • Technical SEO audits and remediation. Crawl issues, indexation problems, Core Web Vitals, schema, redirects, canonical issues, internal linking — across mostly WordPress sites (some with LearnDash, WooCommerce, FunnelKit). • Keyword research and content strategy. Identify ranking opportunities, build content briefs, and work with our content team or write yourself when the project calls for it. • On-page optimization. Title tags, meta descriptions, headings, internal linking, content depth, entity coverage. We expect you to know modern SEO, not 2015 SEO. • Link building. Run real link building campaigns — digital PR, HARO/Qwoted-style work, niche placements, broken link reclamation, strategic guest contributions. Earned links, not bought lists. • Local SEO. Several clients are regional or multi-location. Google Business Profile management, citations, local landing page strategy. • AI-powered workflows. Use Claude (or comparable AI tools) to analyze data at scale, accelerate audits, batch content briefs, parse SERPs, and generally move faster without sacrificing quality. We expect you to have already built workflows like this, not to be exploring them for the first time on our dime. • Reporting and analysis. Pull data from GSC, GA4, Google Tag Manager, Ahrefs/SEMrush, and our reporting stack (Windsor.ai). Translate numbers into clear narratives clients can act on. • Strategic recommendations. Tell us what's working, what isn't, and what to do next. We value people who push back with data over people who just execute tickets. • Collaboration with paid and dev teams. SEO doesn't live in a silo at our shop. You'll coordinate with our PPC and development work to make sure technical changes don't break rankings and that paid and organic strategy reinforce each other. Must-Haves • 5+ years of hands-on SEO experience, including agency or multi-client environments. • Demonstrated results getting clients ranked, cited, or surfaced inside AI search products (ChatGPT, Perplexity, Google AI Overviews, Claude, etc.). A clear GEO strategy and a playbook you can implement from day one. • Past experience running link building campaigns with demonstrated, verifiable results. Be ready to show what you built, how you built it, and what it produced. • Demonstrated wins on technical SEO projects — not just "I worked on the team that did this," but specific issues you diagnosed and fixed with measurable outcomes. • Strong WordPress fluency. You should know your way around Yoast/Rank Math, plugin conflicts that affect SEO, and how to communicate with developers about technical fixes. • Solid command of GA4, Google Search Console, Google Tag Manager, and at least one of Ahrefs, SEMrush, or Sistrix. • Working AI productivity stack. You have built workflows around Claude (or other LLMs) to analyze SEO data at scale — SERP parsing, content gap analysis, log file review, bulk audits, brief generation. Show us the workflow, not just the tool list. • Comfort with structured data (schema.org), redirects, server-side issues (robots.txt, sitemaps, status codes), and Core Web Vitals. • Excellent written English. You'll be writing reports, content briefs, and sometimes client-facing emails. • Self-directed work style. We tell you the goal, you build the path. • Verifiable references. We will ask for specific references from past clients or employers, and we will call them. If that's a problem, this isn't the role for you. Nice to Have • Experience with LearnDash or other LMS platforms (one of our largest accounts is education- focused). • WooCommerce SEO experience — product schema, faceted navigation, category page optimization. • Familiarity with Windsor.ai, Looker Studio, or BigQuery for reporting. • Basic comfort with HTML/CSS and reading PHP (you don't need to write code, but you should be able to read a template and understand what it's doing). • Local/multi-location SEO at scale (state-by-state or city-by-city expansion). • Experience with content production workflows — briefs, editorial calendars, working with writers. What We're Not Looking For • Agencies or resellers. We want to work directly with the person doing the work. • Generalists who do "a little SEO" alongside five other services. • Anyone whose strategy starts with mass directory submissions, PBNs, or AI-generated content at scale. • People who can talk about GEO and AI search but can't show specific work that produced specific results. • Anyone unable or unwilling to provide checkable references. Engagement Details • Type: Long-term contract. We're not hiring for a one-off project. • Hours: Starting around 20 hours/week with room to grow into a larger ongoing engagement based on fit. • Schedule: Flexible, but we need overlap with US business hours (Central Time) for client calls and team coordination. • Communication: Slack for daily work, Zoom for weekly check-ins, project management in our internal tools. • Rate: Open. Tell us your rate and we'll evaluate against the value you bring. How to Apply In your proposal, please include: • A short intro — who you are and why this role interests you. • Two specific SEO wins from the past 18 months. Include the problem, what you did, and the measurable result. Skip the case studies that are just screenshots of traffic going up; we want the why behind the curve. • One specific GEO / AI search win. What client, what platform (ChatGPT, Perplexity, AI Overviews, etc.), what you did, and how you measured it. • One link building campaign you ran. The strategy, the execution, and the verifiable outcome — links earned, referring domain quality, and any traffic or ranking impact. • A short description of an AI-powered workflow you've built and use regularly (Claude or otherwise). What problem it solves, what it replaced, and roughly how much time it saves. • Your typical reporting cadence and what your client communication looks like. • Two references we can call. Name, role, company, and the work you did for them. We will actually call. • To confirm you read this carefully, start your proposal with the word "Compass." We read every proposal that follows the instructions. Generic boilerplate gets passed over. Looking forward to working with the right person. — The Creative Heights Team

We are seeking an experienced Full-Stack AI Product Engineer to help build a secure AI-powered business application for regulated organizations. This project involves building a professional AI platform with document analysis, structured AI workflows, knowledge-base integration, user login, admin controls, and downloadable business outputs. This is not a basic chatbot or prompt-only project. We are looking for someone who has built real AI applications, preferably SaaS products, secure portals, or AI tools for business, legal, risk, compliance, financial services, or other regulated environments. Key Skills Required: --Full-stack web application development --AI application development --RAG / knowledge-base architecture --Document upload and document analysis --OpenAI, Azure OpenAI, Anthropic, or similar AI model experience --Vector database experience --Secure user authentication --Role-based access controls --Secure file storage --Admin dashboard development --AI workflow or agent development --PDF, Word, and Excel report generation --Cloud deployment experience --API integration experience --Strong documentation and handoff practices Preferred Experience: --SaaS platform development --Financial services, legal tech, compliance, risk, cybersecurity, or regulated-industry experience --Building AI tools that analyze uploaded documents and produce structured outputs --Enterprise security, data privacy, audit logs, and customer data separation Important Requirements: The selected developer must be comfortable working under an NDA and IP agreement. All platform design, prompts, workflows, templates, scoring logic, documentation, source code, and related work product created for this project will be owned by our company. The developer may not reuse, resell, repurpose, publish, or train other tools using our materials, concepts, client data, workflows, or proprietary information. To Apply, Please Provide: --Examples of AI tools, SaaS platforms, or secure web applications you have built --Your experience with RAG, document analysis, and AI workflows --Your recommended technology stack for a secure AI business platform --Estimated MVP timeline --Estimated cost or pricing structure --Whether you work alone or with a team --How you handle data security, confidentiality, and IP ownership We are looking for someone who can think like a product builder, build securely, communicate clearly, and help create a professional AI platform suitable for regulated business users.

Company Overview Pay Ready is a leading provider of innovative payment solutions tailored for the property management industry. We help property owners and managers streamline financial processes and accounts receivable functions, including processing current and post-resident rent payments and recoveries. As we integrate Generative AI (GenAI) across our operations, we're seeking a Senior Software Developer to drive the development of AI-powered solutions that enhance both internal workflows and customer-facing applications. Position Overview Joining our team as a Senior Software Developer – Generative AI means being at the forefront of innovation, working on cutting-edge projects that are shaping the future of AI and machine learning. You'll have the opportunity to collaborate with top experts in the field, contributing to groundbreaking research and development that has real-world impact. We offer a dynamic and collaborative work environment where your ideas and contributions are valued, and where you'll have the resources and support needed to bring your vision to life. Being part of our team means embracing a culture that fosters continuous learning and professional growth, with access to ongoing training and development opportunities. You'll work on diverse and challenging projects, gaining valuable experience and expertise that will set you apart in your career. Key Responsibilities - Design and develop AI-driven applications that address both internal operational needs and external client requirements. - Utilize frameworks such as LangGraph and LangSmith to build, orchestrate, and monitor AI workflows. - Implement solutions that integrate seamlessly with existing systems, ensuring reliability and scalability. - Work in tandem with project managers and product owners to understand project scopes, timelines, and deliverables. - Participate in sprint planning, code reviews, and team meetings to ensure alignment and timely delivery of projects. - Provide technical insights and recommendations during the planning and execution phases. - Develop and refine AI models, ensuring they meet performance and accuracy benchmarks. - Monitor and analyze AI application performance, making necessary adjustments to optimize outcomes. -Stay updated with the latest advancements in AI and machine learning to incorporate best practices into development processes.

Summary Senior Full-Stack Developer with experience in JavaScript, python, nodeJS, php.

 We are building a multi-tenant AI-powered marketing operating system for SMBs. 

This is NOT an autonomous AI agent project.

 The platform uses deterministic workflow orchestration enhanced with AI services for:

* content generation,
* approvals,
* publishing,
* engagement analysis,
* brand-style learning,
* multi-platform social posting, * social media campaign.

 We need a senior engineer who understands production SaaS architecture, workflow reliability, API integrations, queues/retries, and AI integrations.

 REQUIRED EXPERIENCE:

* Multi-tenant SaaS applications
* Queue/retry systems
* Webhook reliability
* Idempotency / duplicate prevention
* API integrations (multiple social media platforms)
* Structured AI outputs (JSON schema validation)
* Background jobs / async workflows
* Production-grade backend architecture

 YOU SHOULD UNDERSTAND

* deterministic workflow orchestration,
* retries/backoff,
* distributed locks,
* tenant isolation,
* workflow state management,
* structured AI pipelines,
* cost governance,
* approval workflows.

 DO NOT APPLY IF YOUR EXPERIENCE IS MOSTLY:

* autonomous AI agents,
* chatbot-only projects,
* prompt engineering only,
* no backend SaaS experience.

 Project Scope:

* starting with 50 concurrent clients
* AI-generated social content
* approval-gated publishing
* multi-platform posting
* adaptive brand memory
* analytics + engagement tracking * paid social media campaigns

 To apply, please provide:

 1. Relevant SaaS/backend projects
 2. Experience with OpenAI structured outputs
3. Your preferred architecture approach for scalable workflow systems

Overview We're building an open-source CLI gateway for multi-agent AI orchestration — model-agnostic, MCP-native, and designed to bring any agent framework online with a single command. The repo is active, well-documented, and growing. We need an engineer to accelerate integration coverage and help attract open-source contributors. The Work Build agent templates and runnable examples for LangGraph, CrewAI, and similar frameworks Add LLM provider support (Groq, Mistral, Gemini, etc.) to the Hermes runtime Write clean, contributor-friendly code that models good PR hygiene Submit work via fork → PR → merge workflow on GitHub You Are Strong Python developer with CLI tooling experience Familiar with at least one of: LangGraph, CrewAI, LiteLLM, LangChain Comfortable with open source GitHub workflows (fork, PR, issues, reviews) Self-directed — you read docs, ask good questions, and don't wait to be unblocked Nice to Have Experience with MCP (Model Context Protocol) Familiarity with SSE, OAuth 2.1, or agent credential management Prior open source contributions Engagement Part-time to start, 20 hrs/week Fixed milestones per integration delivered Potential to grow with the project To Apply Share your GitHub profile and one example of open source work or a project that shows your Python and agent framework experience. https://github.com/ax-platform/ax-gateway

We are building a next-generation workflow automation platform that combines deterministic business rules, artificial intelligence, document intelligence, and human review workflows into a single operating system. This is not a traditional CRM project. Our vision is to develop a doctrine-driven platform where business rules serve as the system authority, AI serves as an analytical and drafting layer, and human reviewers serve as the final compliance checkpoint. We are seeking an experienced engineer or engineering partner who can help architect and build the platform from the ground up. Project Objectives The platform will: • Ingest and analyze large volumes of structured and unstructured documents • Extract data from reports, PDFs, and supporting documentation • Apply rule-based workflow logic • Generate AI-assisted recommendations and draft outputs • Maintain complete audit trails and workflow transparency • Route work through human review checkpoints • Support future deployment of local AI infrastructure for privacy and performance Core Architecture The system will be built around four primary layers: 1. Rules Engine * Deterministic business logic * Workflow orchestration * State management * Trigger and escalation logic * Audit tracking 2. AI Layer * Document analysis * Classification * Pattern detection * Summarization * Draft generation * Structured outputs 3. Local Processing Layer * OCR * Document parsing * Data extraction * Vector search * Local inference capabilities * Privacy-first processing 4. Human Review Layer * Quality assurance * Workflow approvals * Compliance review * Exception handling Initial Development Priorities Phase 1 • User authentication • Client record management • Document upload system • OCR and document extraction • Workflow engine • Rule-based status management • Review dashboard Phase 2 • AI-powered document analysis • Automated classification • Recommendation engine • Draft generation workflows • Response parsing Phase 3 • Local AI infrastructure • Vector database integration • Knowledge retrieval system • Multi-agent workflow orchestration • Advanced automation Desired Technical Experience Required • React / Next.js • Node.js, Python, or similar backend framework • PostgreSQL or equivalent relational database • REST APIs • Cloud infrastructure (AWS, Azure, or GCP) • Workflow automation systems • Document processing pipelines Preferred • OpenAI APIs • Anthropic APIs • Retrieval-Augmented Generation (RAG) • LangGraph, LangChain, or similar frameworks • Vector databases • OCR technologies • AI agent architectures • NVIDIA AI ecosystem • Local model deployment What We Are Looking For We are not looking for someone who simply builds forms and dashboards. We are looking for a builder who understands how to combine: • Rules engines • Artificial intelligence • Workflow automation • Human review systems • Scalable software architecture The ideal candidate enjoys solving complex business process problems and translating expert decision-making into software systems. Engagement Structure Open to: • Fractional CTO • Lead Architect • Senior Full-Stack Engineer • AI Systems Engineer • Development Agency • Long-term strategic technology partner To Apply Please provide: • Relevant project examples • Experience building workflow automation platforms • Experience with AI-powered applications • Technology stack recommendations • Estimated availability • Preferred engagement structure