I need an expert senior software engineer that can provide consulting services around implementation best practices of LLM's and AI into existing application workflows. i.e. leveraging AI to extract data from a document as part of an ingestion pipeline.

We are looking for a skilled Full-Stack Developer with experience in AI and software engineering to support client communication and technical requirement gathering. In this role, you will be responsible for engaging directly with stakeholders through calls, understanding their technical and business needs, and accurately translating those requirements into clear, actionable documentation for the development team. The ideal candidate should have a strong technical background in full-stack development, AI systems, and modern software architecture, enabling them to ask the right questions, validate assumptions, and ensure that project requirements are correctly captured without ambiguity. You will act as a bridge between clients and engineering teams, ensuring smooth communication and reducing misunderstandings during project execution. Responsibilities include conducting requirement-gathering calls, clarifying technical specifications, documenting system needs, and collaborating closely with developers and product teams. Strong understanding of AI-driven systems, web technologies, and software development workflows is essential to perform effectively in this role. We are seeking someone who can combine technical expertise with clear communication skills, ensuring that complex requirements are translated into structured, developer-ready specifications that support successful project delivery.

Forum Intelligence: Project Brief & Initial Rollout 1. Executive Summary & Objective Forum Intelligence is a beginning as a localized data retrieval, processing, and archiving system designed to scrape public municipal records and state legislative data for public oversight. The immediate objective is to build a functional, highly resilient prototype focused on the Tri-Cities region (Burbank, Glendale, and Pasadena, California). The system will autonomously ingest messy, unstructured municipal data (City Council meeting minutes, agendas, public notices, and legislative PDF text, recorded mp4), clean it, and make it fully searchable and queryable via a localized AI agentic framework. 2. Phase 1 Scope: The Tri-Cities Rollout Th engineer will be responsible for building two primary pillars: A. Resilient Scraper Bots • Target Ingestion: Monitor and pull data from Burbank, Glendale, and Pasadena municipal portals and California legislative feeds. • Data Types: Brittle HTML sites, heavily nested tables, public notices, legislative drafts, and massive unstructured PDF archives. • Requirements: The scraping architecture must be exceptionally robust, utilizing intelligent error handling, retry semantics, and pagination tracking to handle frequent municipal website layout changes without breaking the pipeline. B. Ingestion & Vector Pipeline • Parsing: Extracting clean text from poorly formatted documents and scanned PDFs. • Local RAG (Retrieval-Augmented Generation): Chunking and embedding the data locally into a vector database (e.g., pgvector, Chroma, or Milvus) to enable semantically accurate entity linking and contextual search. 3. Targeted Hardware Stack To ensure maximum data security, strict public oversight integrity, and predictable operational costs, Forum Intelligence is skipping commercial cloud APIs in favor of an on-premise, localized NVIDIA enterprise deployment. The production roadmap aligns precisely with the new computing patterns detailed in NVIDIA’s latest hardware roadmap: • Inference & Token Generation: Running local open-weight frontier models (e.g., Neotron 3 Ultra or Claude/Llama equivalents) optimized for reasoning and long-context tool use. • Compute & Orchestration: The backend infrastructure is architected around NVIDIA’s dedicated agentic architecture, utilizing high-instructions-per-clock (IPC) Vera CPUs paired with Vera Rubin GPUs. • Memory & Storage Processing: Utilizing NVIDIA’s unified memory fabric and data processing units (DPUs) for ultra-low latency context management, KV caching, and fast vector database retrieval. 4. Immediate Milestones for the Engineer 1. Architecture Design: Map out the database schema and local inference ingestion loop. 2. Tri-Cities Scraper Deployment: Write and deploy the initial automated bots for Burbank, Glendale, and Pasadena. 3. Local MVP Pipeline: Demonstrate a local RAG pipeline where a user can query the Tri-Cities scraped records and receive grounded answers with exact source attributions. The above was AI generated from months long conversations with Gemini. The goal is to prove the concept then roll out to LA County, state of CA, and then the country.

Description: I’m a non-technical founder building SoCalForeclosures.net — a subscription platform for Southern California real estate investors. Lead Members pay $149.99/month (capped at 8,000) to access scored off-market foreclosure and pre-foreclosure leads. Members work leads in a built-in CRM and sell deals through an internal marketplace to cash buyers (free tier or $99.99/month First Look). A working prototype is already built and deployed. Core features including user authentication, PayPal payments, marketplace (SoCalDeals), MyCRM pipeline, Phantom lead scoring engine, admin tools, and bot management screens are functional with demo data on a professional dark theme. Current honest status: The automated “bot army” that will pull real public distress signals from county recorders, courts, tax collectors, legal newspapers, trustees, and paid data sources is scaffolded but not yet actively ingesting live leads. A detailed signal catalog and county data sources are already documented. Project Scope (Fixed Price): I need an experienced senior full-stack developer to take the existing prototype and deliver a fully functioning, production-ready platform that is live and online. This is a single fixed-price engagement. Key deliverables for this project: Full code review and audit of the current Next.js + Express + PostgreSQL + Prisma codebase Polish and improve visual design and user experience across the member dashboard, lead feed, CRM, and marketplace so it looks professional for serious real estate investors Activate and productionize the real data pipeline (bot army) so it can ingest actual leads from public and paid sources according to the existing signal catalog Fix bugs, performance issues, technical debt, and operational problems Migrate hosting from the current European server to a reliable US-based provider with proper deployment pipeline, monitoring, and backups Stabilize the site so it runs reliably in production Deliver clear documentation and handover Important notes: This is not a from-scratch build. A substantial amount of the website and backend already exists and is deployed. The goal of this fixed-price project is to complete the remaining work and launch a fully functioning, live platform with real data capabilities. Once the website is successfully deployed live and online, we will negotiate a separate ongoing contract for maintenance, upgrades, new features, and additional work (including potential iOS and Android mobile apps). Tech stack: Next.js 14 (App Router) + TypeScript + Tailwind Express backend + PostgreSQL + Prisma Existing TypeScript bot framework (Playwright / Cheerio) PayPal payments, Twilio, Resend, Mapbox Ideal candidate: Senior full-stack developer with strong experience in TypeScript, Next.js, Prisma/PostgreSQL, and data pipelines or web scraping (public/government data sources) Experience taking prototypes to production, including hosting migrations and operational stability Comfortable working with an existing codebase and delivering clear recommendations to a non-technical founder Proactive, reliable, and quality-focused Project type: Fixed Price (one set price for the full scope above to get the platform fully live and functioning). To apply, please: Propose your fixed price for completing this project (review + polish + activate data pipeline + hosting migration + full production launch). Share 1–2 examples of similar past work (taking existing code to production, data platforms, or marketplaces). Briefly describe how you would approach reviewing and completing an existing prototype. Confirm your experience with US hosting providers and data pipeline / scraping work. Any questions about the current state or scope. Serious applicants will receive the full technical documents (Developer Brief, Signal Catalog, and County Data Sources) under NDA. Project owner is based in Southern California. US time zones preferred for easier communication.

Dear Universe, Please send me someone who can automate our workflows. Someone who looks at our WordPress, WooCommerce, HubSpot, Monday, and Make stack and just... knows what needs to happen. Because God knows I've been through the manual emails, the spreadsheet hell, the constant back-and-forth with clients on onboarding, the processes that should've been automated months ago, and dealing with people who are wishy-washy about their commitment. Look, I'm really good with people, I'm good at design, I'm good at ideas... but holding all the mental load of architecting workflows and automation systems? That's not my thing. There's gotta be somebody out there with a really smart, healthy, analytical brain who can help me plan it right, diagram it properly, and architect this like an adult. Someone who does it right the first time. I need a workflows engineer who gets it, someone who can build a client-facing dashboard so our onboarding process runs itself, without me sending a single manual email. If you think you're a good fit, answer as if you're The Universe responding to my plea. Let me know why you're the one, and I'll know you actually read this. Thanks, Universe. Let's see what you got.

We are seeking a Claude expert to develop and enhance our AI tool. to integrate all of my marketing using constant contact email and texting. also wanting to integrate all work so I don't have to deal with the mundane. The ideal candidate will have extensive experience with Claude and be able to integrate it into our existing systems. Responsibilities include developing new features, optimizing performance, and ensuring seamless integration with our current infrastructure. The role requires a strong understanding of AI technologies and the ability to work independently.

Bellementis PLLC is seeking a contract legal automation specialist to help design and implement practical automation workflows for a fast-growing boutique law firm. The ideal candidate has experience with law firm operations, document automation, AI tools, workflow design, and systems such as Microsoft 365, Clio, NetDocuments, Gavel, Zapier, Notion, or similar platforms. Responsibilities may include: Automating client intake, engagement letters, matter opening, task tracking, billing workflows, and document generation Building reusable templates, checklists, and workflows Helping integrate AI tools into legal and administrative processes Improving knowledge management and internal firm operations Working with lawyers, operations, and technical team members to turn manual processes into scalable systems This is a contract role. Prior experience with legal tech, law firm operations, document automation, or AI-enabled workflow design is strongly preferred.

# Full-Stack AI Engineer — Semantic Search + Next.js + Supabase (Long-Term, Contract-to-Hire) ## About We're building an AI-native platform that makes a large archive of recorded talks genuinely discoverable and useful: need-based semantic search over transcribed media, with a subscription product built around it. We have a clear product vision and architecture and are looking for a lead engineer to build the first version and grow with us long-term. Full product details are shared with shortlisted candidates under NDA — this post focuses on the engineering and the skills we need. ## The engineering challenge You'll build a two-part system that shares one database: 1. **A content pipeline (Python):** ingest recorded talks, transcribe them, chunk and enrich the transcripts with metadata using an LLM API, generate embeddings, and store everything in Postgres. 2. **A web app (Next.js):** fast, crawler-friendly, SEO-strong content pages with structured data; retrieval-based search that returns relevant source material with links/citations; user accounts; and Stripe-gated paid content. We care a lot about retrieval *quality* and clean, maintainable architecture — this is a real product, not a prototype. ## Required tech stack - **App:** Next.js (App Router), TypeScript, Vercel. Strong SSR/SSG, SEO, and JSON-LD structured-data experience. - **AI/backend:** Python; production RAG (embeddings, chunking, retrieval quality); LLM API integration. - **Data:** Postgres + **pgvector** (via Supabase); embeddings via a hosted model (Voyage/OpenAI). - **Auth & gating:** Supabase Auth with row-level security. - **Payments:** Stripe (subscriptions + one-time). ## Required skills - Shipped production Next.js (App Router) + TypeScript apps with strong SSR/SEO. - Built a real RAG / vector-search system in production — not a tutorial clone. - Comfortable in Python for data pipelines. - Postgres + pgvector and Supabase in production. - Stripe integration. - Plans before building; communicates clearly in writing. ## Nice to have - Audio/video transcription experience (Whisper / faster-whisper / Deepgram / AssemblyAI). - Agentic coding workflows (e.g., Claude Code). - Content-heavy SEO products or media libraries. ## Engagement - Hourly, contract-to-hire. ~20–40 hrs/week to start; long-term for the right person. - We start finalists on a **small paid test project** (a single self-contained slice of the pipeline) before the full engagement — that's how we evaluate fit. ## Confidentiality This is a proprietary product. Shortlisted candidates sign a mutual NDA before we share full scope and context. Please don't expect complete product details in the first exchange — strong technical applicants will have everything they need to be evaluated, and the rest follows the NDA. ## How to apply Applications that skip these are ignored: 1. **Start your proposal with the word `pgvector`** so we know you read this. 2. Link **two** projects: one live Next.js/SSR app, and one RAG/embeddings or LLM-integration project. Tell us what *you* personally built. 3. Answer briefly: *An offline embedding pipeline and a live search query must use the same embedding model — why does that matter, and how would you guarantee it?* 4. One line on your approach to chunking long-form audio/video transcripts for good retrieval.

We are seeking an experienced AI workflow / operations consultant to help us build repeatable “business of the future” blueprints for niche service industries. We are not building a new AI product. We want help identifying the best existing tools, workflows, and automation opportunities to modernize service businesses in a practical, scalable way. We want someone who can help us: map current workflows identify the best opportunities for AI and automation recommend the right tool stack define what should stay human vs. what should be automated create standardized implementation blueprints we can deploy across multiple clients We are looking for someone with real operational depth, not just generic AI enthusiasm. Bonus if you have worked in: healthcare legal compliance-sensitive service businesses CRM / automation / intake / communication systems Please send examples of similar work and explain how you would approach building a scalable modernization blueprint for these kinds of businesses.

We're looking for a contract engineer to lead that transition. The core integrations and workflow already exist and pass their tests. The work now is making them run reliably against live customer systems, hardening the platform for day-to-day operation, and setting up onboarding so we can bring on additional customers without rebuilding. You'll work closely with our CTO, who owns the architecture and data model. Your focus is integration, implementation, and reliability.