We are a fast-growing telecom / AI-First CPaaS serving sms and voice API's. We are building the first AI-first communications platform (SMS, Voice, RCS, AI agents) designed for speed, simplicity, and real-world business outcomes. We are not looking for a “task completer.” We are looking for a true senior engineer who: thinks in systems moves fast makes decisions independently writes clean, scalable code uses AI tools (Claude, etc.) as a force multiplier ⚠️ Read This First *DO NOT APPLY IF YOU ARE PRETENDING TO BE IN A DIFFERENT COUNTRY. PROOF OF RESIDENCY IS REQUIRED. Most applicants will not be a fit. If you need: detailed tickets hand-holding constant direction This is NOT the role for you. If you are the type of engineer who: sees a problem and solves it end-to-end improves architecture without being asked ships quickly without sacrificing quality You will thrive here. What You’ll Do Build and ship full-stack features across our platform (messaging, voice, AI workflows) Make architectural decisions (not just implement) Improve system performance, reliability, and scalability Work directly with founders (no PM layers) Move from idea → production very quickly What We Expect (Non-Negotiable) 5+ years real full-stack experience (not just titles) Strong backend experience (Node.js / APIs / infra) Strong frontend experience (React or similar) Experience building production systems at scale Ability to work autonomously with minimal direction High ownership mentality Bonus (but highly valuable) Experience with telecom / CPaaS / messaging Experience with AI integrations (LLMs, agents, workflows) Experience optimizing performance at scale Startup experience (especially early-stage or fast growth) How We Work Small, high-output team Very fast iteration cycles No unnecessary meetings High trust, high expectations We use AI tools heavily (Claude, etc.) — you should too What We Care About Most Not your resume. We care about: How you think How you build How fast you execute The quality of your code To Apply Please include: Links to projects you’ve built (real production work) A short explanation of: a system you designed end-to-end a difficult technical decision you made independently Your GitHub Optional (but strong signal): Share how you use AI (Claude, etc.) in your workflow Compensation Competitive (based on experience) Long-term opportunity with a fast-growing, profitable company If you are truly senior, this will feel obvious. If not, this role will be very uncomfortable. **THIS IS A FT, HOURLY ROLE. PROVIDE YOUR REQUESTED HOURLY RATE IN PROPOSAL**

Project Overview: We are a fast-paced law firm looking to optimize our entire case pipeline from client intake to matter closure. We use Bridge Legal for marketing intake, Clio for our Core Case Management System (CMS), Jubilee for our bankruptcy practice section, Google Calendar for scheduling court events, and Microsoft 365 (SharePoint/OneDrive) for document storage. Instead of building an expensive custom platform from scratch, we want to leverage a low-code automation system (n8n preferred, or Zapier) coupled with advanced AI APIs (such as Anthropic Claude or OpenAI) to handle data mapping, automated drafting, calendar triggers, and text alerts. Airtable will serve as the primary human control panel for our 17 staff members. Mandatory Legal Compliance & Insurance Prerequisites: Due to strict State Bar legal ethics regulations regarding the absolute confidentiality of client proprietary records, data safety is our highest priority. Do not apply if you cannot meet these criteria: 1. NDA: The selected contractor must sign a comprehensive Non-Disclosure Agreement (NDA) prior to receiving system access. 2. Liability Insurance: You must provide verifiable proof of active Professional Liability Insurance (Errors & Omissions) and Cyber Liability Insurance before contract execution. 3. Data Silo Constraints: All workflows must utilize commercial API tiers providing Zero Data Retention (ZDR). Client documents and pleadings must never be used to train public AI models. Key Scope of Automation Tasks: 1. Airtable Control Center: Build out the primary user interface directly inside Airtable, which is already utilized by our 17 staff members. All automated steps (Intake, Pleading Drafting, SMS triggers, and Case Closures) must be launched via Airtable button triggers, attachment fields, and status fields. The automation must capture the Airtable user metadata to maintain an internal audit trail before passing data to Clio. 2. Lead to Retainer: Catch webhook data from Bridge Legal, prompt an LLM to parse raw intake notes for names and deadlines inside Airtable, and automatically trigger a dynamic e-sign contract template (DocuSign/Gavel/HelloSign). 3. Payment to Clio/Jubilee Creation: Listen for payment webhooks (Stripe/LawPay) and use the Clio API to programmatically open the Account, Contact, and Matter. Our bankruptcy section uses Jubilee which is natively connected to Clio via a live sync. The candidate must ensure cases routed through our bankruptcy pipeline are cleanly initiated in Clio so that the native Clio-to-Jubilee data bridge operates smoothly without synchronization lag. 4. AI Answer Generation via SharePoint: Set up an automated folder monitor in Microsoft SharePoint. When a Plaintiff's Complaint PDF is uploaded, the automation must extract the text, run it through Claude 3.5 Sonnet to draft paragraph-by-paragraph denials, append a baseline library of Affirmative Defenses, and save a formatted .docx back to SharePoint and Airtable. 5. Google Calendar to Twilio Reminders: Check our synced Google Calendar daily for court appearances, look up the corresponding client phone numbers using Clio's API, and schedule automated text reminders via Twilio at 30, 7, and 1-day intervals. Implement protective logic (idempotency) to ensure a client is never double-texted. 6. Accounting & Case Closure: Read settlement figures from Airtable fields, query the Clio Expenses API to subtract advanced costs, calculate our firm split using formulas, and automatically execute a Clio API update to switch the matter status to "Closed." Airtable Schema Requirements: The candidate will design a relational, multi-view database structure in Airtable. This database will serve as the primary operational hub, containing tables for: • Table 1: Matters & Intake (Master ledger for lead parsing, case categorization, and user audit stamps). • Table 2: Automation Control Center (Action buttons for contract deployment, e-sign status webhooks, and the AI file drop zones). • Table 3: Settlement Ledger (Calculated currency tracking fields for Gross Settlement, Firm Fee %, Advanced Clio Costs, Medical Liens, and Net Client Payout). The backend code must interact directly with Airtable fields to manage state progression, receive user tracking data, deposit AI-generated documents, and pull transaction balances. Required Experience & Technical Proficiencies: • Proven track record building multi-step automations inside n8n or Zapier. • Experience authenticating and mapping data variables natively via the Clio API (v4), Google Calendar API, and Microsoft Graph / SharePoint API. • Demonstrated experience handling structured JSON payloads and dealing with API rate limits. • Strong understanding of AI prompt design for accurate textual parsing and document structural layout.

We are a fast-growing telecom / AI-First CPaaS serving sms and voice API's. We are building the first AI-first communications platform (SMS, Voice, RCS, AI agents) designed for speed, simplicity, and real-world business outcomes. We are not looking for a “task completer.” We are looking for a true senior engineer who: thinks in systems moves fast makes decisions independently writes clean, scalable code uses AI tools (Claude, etc.) as a force multiplier ⚠️ Read This First *DO NOT APPLY IF YOU ARE PRETENDING TO BE IN A DIFFERENT COUNTRY. PROOF OF RESIDENCY IS REQUIRED. Most applicants will not be a fit. If you need: detailed tickets hand-holding constant direction This is NOT the role for you. If you are the type of engineer who: sees a problem and solves it end-to-end improves architecture without being asked ships quickly without sacrificing quality You will thrive here. What You’ll Do Build and ship full-stack features across our platform (messaging, voice, AI workflows) Make architectural decisions (not just implement) Improve system performance, reliability, and scalability Work directly with founders (no PM layers) Move from idea → production very quickly What We Expect (Non-Negotiable) 5+ years real full-stack experience (not just titles) Strong backend experience (Node.js / APIs / infra) Strong frontend experience (React or similar) Experience building production systems at scale Ability to work autonomously with minimal direction High ownership mentality Bonus (but highly valuable) Experience with telecom / CPaaS / messaging Experience with AI integrations (LLMs, agents, workflows) Experience optimizing performance at scale Startup experience (especially early-stage or fast growth) How We Work Small, high-output team Very fast iteration cycles No unnecessary meetings High trust, high expectations We use AI tools heavily (Claude, etc.) — you should too What We Care About Most Not your resume. We care about: How you think How you build How fast you execute The quality of your code To Apply Please include: Links to projects you’ve built (real production work) A short explanation of: a system you designed end-to-end a difficult technical decision you made independently Your GitHub Optional (but strong signal): Share how you use AI (Claude, etc.) in your workflow Compensation Competitive (based on experience) Long-term opportunity with a fast-growing, profitable company If you are truly senior, this will feel obvious. If not, this role will be very uncomfortable. **THIS IS A FT, HOURLY ROLE. PROVIDE YOUR REQUESTED HOURLY RATE IN PROPOSAL**

What Is Already Done Everything is built and ready. You are not designing or coding from scratch. You are deploying and connecting services. • 24 screens built in React — fully designed and coded • Complete Node.js backend server — all routes written • All payment logic written — just needs Square keys connected • AI agent integration written — just needs API key connected • Legal pages done — Privacy Policy and Terms of Service • App Store submission kit ready • Logo and brand assets ready • Developer notes with full instructions provided • Environment variables template with Square sandbox key pre-filled • All third party integration code provided with examples What I Need You To Do Website: • Push all code to private GitHub repository • Deploy React frontend to Vercel with my custom domain • Deploy Node.js backend to Railway • Set up Supabase database with all required tables • Connect Square API for all payment flows • Connect Google Sign In and Apple Sign In • Connect Daily.co for video calls • Connect Resend for email notifications • Connect Supabase Realtime for live messaging • Set up Expo push notifications • Set up Supabase Storage for file uploads • Test all Square payment flows in sandbox first • Switch to Square production after my approval • Get website fully live at my custom domain Mobile App: • Convert all 24 web screens to React Native using Expo • Test on both iPhone and Android • Submit to Apple App Store • Submit to Google Play Store Tech Stack • Frontend: React 18 • Mobile: React Native with Expo • Backend: Node.js with Express • Database: Supabase • Frontend hosting: Vercel • Backend hosting: Railway • Payments: Square API • AI: Anthropic Claude API • Video: Daily.co • Email: Resend • Auth: Google OAuth and Apple Sign In • Storage: Supabase Storage • Realtime: Supabase Realtime

AI Automation Engineer – Personal Injury Law Firm (Phase 1) Overview We are a plaintiff personal injury law firm seeking an experienced AI automation engineer to build a practical AI-powered operations system that reduces administrative workload and improves case management. Firm Profile: - 1 Attorney - 1 Legal Assistant - Approximately 100 Active Cases - Approximately 25 Cases in Litigation We are not looking for chatbots, prompt engineering, or marketing automation. We are seeking a builder who can deploy production-grade workflow automation integrated with our existing systems. --- Existing Technology Stack - CASEpeer - Supio - Gmail (Google Workspace) - Google Calendar - Google Drive - Claude - ChatGPT - CoCounsel - PLAUD --- Phase 1 Objective Build a Daily Case Command Center and Follow-Up System. The goal is to ensure that every morning the attorney knows exactly which files require attention and why. --- Deliverable #1: Daily Case Command Brief Generate a daily briefing containing: Litigation Matters - Upcoming depositions - Discovery deadlines - Hearings - Expert deadlines - Outstanding litigation tasks Pre-Litigation Matters - Treatment complete but no demand - Missing medical records - Records requests outstanding more than 21 days - Demands pending more than 30 days - Settlement checks outstanding Communications - Unanswered client emails - Unanswered adjuster emails - Unanswered defense counsel emails - Communications requiring attorney attention Case Velocity - Stale files - Cases with no recent activity - Recommended next actions --- Deliverable #2: Gmail Intelligence The system should: - Monitor designated Gmail inboxes and labels - Identify case-related emails - Extract action items - Detect deadlines - Identify follow-up opportunities - Draft suggested responses --- Deliverable #3: Follow-Up Automation Generate draft communications for approval: - Medical records requests - Provider follow-ups - Adjuster follow-ups - Client status updates - Scheduling communications No communication should be sent automatically. Human approval is required before sending. --- Deliverable #4: Calendar & Reminder Automation Create and manage: - Follow-up reminders - Litigation reminders - Discovery reminders - Records request reminders - Suggested calendar events --- Deliverable #5: CASEpeer Integration Where supported by available integrations/APIs: - Create tasks - Create notes - Associate communications with matters - Maintain activity history --- Technical Requirements Required: - n8n - Python - OpenAI API - Anthropic API - Gmail API - Google Calendar API - Google Drive API - REST API integrations Strongly Preferred: - LangGraph - LangSmith - Google Workspace administration - Salesforce integrations - CASEpeer, Clio, or Filevine experience - Legal technology experience - HIPAA or regulated-data experience --- Security Requirements - Human approval before external communication - Activity logging - Error handling - Retry mechanisms - Secure credential management - Documentation of workflows --- What Success Looks Like The system should: - Reduce administrative workload - Improve follow-up consistency - Reduce stale files - Improve litigation oversight - Improve case visibility - Provide a daily prioritized action plan --- Application Requirements Please include: 1. Similar workflow automation projects you have completed. 2. Experience with n8n and AI workflow automation. 3. Experience integrating Gmail and Google Workspace. 4. Experience integrating CRM or case-management systems. 5. Proposed architecture for this project. 6. Estimated timeline. 7. Estimated fixed-fee budget. Begin your application with: CASECOMMAND Applications without this keyword will not be considered. --- Budget Expected Phase 1 Budget: $8,000–12,000 Preference will be given to candidates who can demonstrate production deployments rather than proof-of-concept or prompt-engineering projects.

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.

Google Workspace & MCP Security Consultant Quick Consultation | 2-3 Hour Engagement About This Role We're a lean 4-person team looking for a Google Workspace and MCP specialist to help us get our Google Workspace permissions right before we integrate Claude and Cowork. We need someone who can audit our current setup, advise on least privilege access, help us understand how to set up per-employee credential scoping, and train our team on best practices—all in a focused 2-3 hour session. This is a quick, targeted engagement. You'll come in, review our setup, advise on the right architecture, walk us through the key configurations, and leave us with clear documentation we can follow ourselves. What You'll Do Quick Audit: Review our Google Workspace setup (30 min) and identify any obvious permission gaps or security issues Least Privilege Recommendation: Advise on the right permission model for a small 4-person team integrating Claude/Cowork with per-employee scoping Google MCP Overview: Explain how to set up Google MCP servers and OAuth credential flow so each team member can authorize their own data access Live Walkthrough: Show us the key steps to implement this—OAuth setup, permission scopes, service account considerations for small teams Q&A + Documentation: Answer our questions and leave us with a one-page checklist or runbook so we can execute this ourselves Training: Spend 20-30 min with our whole team explaining the setup so everyone understands what permissions they're granting and why Required Experience Solid hands-on experience with Google Workspace and Google Cloud IAM (at least 2+ years) Practical experience setting up OAuth 2.0 flows, service accounts, and API credential management Experience with Model Context Protocol (MCP) servers and Google MCP setup—or strong API integration background Understanding of least privilege access control and how to scope permissions appropriately Ability to explain technical security concepts clearly to non-technical people (we're a small team, not security experts) Quick learner who can assess a setup and provide targeted advice efficiently Nice-to-Haves Familiarity with Claude, Anthropic's MCP ecosystem, or Cowork Experience working with small teams or startups (you get what it's like to be lean) Google Cloud Fundamentals certification Track record of clear documentation and teaching non-technical people Engagement Details Scope: 2-3 hour focused consultation (can be done in one or two sessions) Format: Zoom/virtual session(s) with screen sharing. Ideally all 4 team members present for at least part of it Location: Remote (we're based in Huntington Beach, CA) Rate: $200-300 total for 2-3 hours, or your standard hourly rate ($75-100/hr is typical for this expertise) Timeline: ASAP—we're ready to move forward. Deliverables: A one-page implementation checklist, notes from the session, and any code snippets or OAuth setup guidance we'll need to execute this ourselves Send us a quick message with: Your background—especially with Google Workspace and MCP/OAuth work Your availability in the next 1-2 weeks (what days/times work for 2-3 hours?) We're a small team that values privacy and does things the right way. If you know your stuff and can help us set this up correctly, we'd love to work with you!

We are seeking an AI Integration Specialist & Solution Architect to enhance our platform with advanced AI capabilities. The role involves integrating AI tools like Claude and GPT to improve user experience and automate processes. The ideal candidate will have experience in solution architecture and a strong understanding of AI technologies.

We are independent technology advisors that specialize in helping Salesforce customers choose phone, communication, document, and AI platforms for their business. We would like to create a series of videos for our youtube channel that are product demonstrations of our technology partner solutions that integrate with Salesforce. Example providers: Dialpad, Zoom, Five9, Incontact, Aircall, Docusign, Anthropic / Claude and many more. Product demo videos should be about 5 minutes each that showcase the platforms standard features, standout/unique features, Salesforce integration options including Open CTI, standard API (browser extension), and Salesforce Voice. Videos should be working demos of these products and features as you talk about the different features. Content should be professional and friendly and most importantly, human. Your face is representing our brand, so it is important that you are comfortable in front of the camera similar to youtubers showcasing products or making reaction videos. These trials can be set up in a free salesforce developer account and we can work with providers on getting access as needed to create the content. Cost per video will be negotiable. There will be at least 15-20 videos made over the next 1-3 months as a part of this series, with room to grow. Check out www.commcorrect.tech for more info about our company

DESCRIPTION We're a small applied AI lab running a live, production-track AI product for an institutional financial services client. The work is technical, fast-moving, and high-stakes. We need to fill a critical infrastructure role with someone senior, collaborative, and genuinely excited about building in the current AI tooling ecosystem. THE ROLE You'll own the data infrastructure layer for an AI-powered intelligence platform built on the Microsoft Azure ecosystem. This is a hands-on engineering position — you're responsible for designing, building, and maintaining the pipelines that feed a live AI scoring engine. The environment is agentic. Data moves from 15+ heterogeneous external sources (APIs, PDFs, regulatory filings, web) through Bronze, Silver, and Gold layers into a scoring and inference system. The hard problems are extraction quality, schema normalization, pipeline reliability, and getting the right data to the scoring engine in the right shape. You'll work directly with the technical lead and engagement lead. No layers. Fast decisions. WHAT YOU'LL OWN + Data pipeline architecture and delivery across Bronze (raw ingestion), Silver (normalization, NLP extraction, entity resolution), and Gold (unified output, scoring-ready) layers + Microsoft Fabric lakehouse implementation — OneLake, Data Pipelines, Dataflows Gen2, Warehouse, and downstream system integration + Microsoft Foundry (formerly Azure AI Studio) — agent orchestration, prompt pipelines, and AI model integration within a secure Azure tenancy + Azure Data Factory orchestration for structured source ingestion +Salesforce integration via Snowflake native connector — field mapping, custom object schemas, sync reliability Extraction pipelines for unstructured sources (PDFs, regulatory filings, web content), coordinating with Azure OpenAI-based extraction agents +Data governance and security posture — all data stays within the client's Azure tenancy; data residency is non-negotiable REQUIRED: Technical Skills + Microsoft Fabric — production experience, not sandbox. You should be able to speak to Lakehouse vs. Warehouse tradeoffs, OneLake architecture, and real pipeline implementation. Microsoft Foundry / Azure AI Studio — hands-on with agent deployments, prompt flow, model endpoints, and Azure OpenAI integration within an enterprise Azure tenancy + Azure Data Factory — pipeline authoring, trigger management, connector configuration, monitoring +Snowflake — Gold layer data warehousing, schema design, query optimization, native connector usage (specifically Salesforce) + Python — data engineering contexts: pandas, PySpark, API clients, extraction scripts + SQL — complex joins, window functions, schema design; SQL Server preferred + Azure Blob Storage / ADLS Gen2 — Parquet/Delta format, access control, lifecycle management REQUIRED: AI-Augmented Development This is a hard requirement. You should be actively using AI coding tools to multiply your output — fluency with Claude Code, Cursor, and OpenAI Codex as part of your daily development workflow. If these aren't already in your stack, this isn't the right fit. We hire for multiplied output, not raw hours. REQUIRED: Demonstrable Work We don't evaluate resumes alone. Bring something — a GitHub repo, a deployed pipeline, an architecture document you authored, a case study with real numbers. We should be able to look at your work and understand what you built, what decisions you made, and why. Work under NDA is fine if you can describe it in enough detail to convey complexity and ownership. ATTITUDE & WORK STYLE Comfortable with Agile Scrum and its accompanying ceremonies. You raise issues early and help solve them. You communicate tradeoffs clearly without over-explaining. You're comfortable with evolving specs and don't need to win the architecture argument — just build the right thing within the approved stack. We're a small, senior team with low friction and direct communication. That's the environment; it works if you work with it. THE STACK The client environment has specific technology approvals. Production work runs on Azure OpenAI (client-hosted), Microsoft Fabric, Microsoft Foundry, Snowflake, Azure Data Factory, ADLS Gen2, Salesforce via Snowflake native connector, and SQL Server. LangChain, DeepSeek, and the external Claude API are not approved for this environment. NICE TO HAVES Experience with financial services or institutional investment data (SEC EDGAR, public pension filings, regulatory documents), familiarity with InvestorFlow or Salesforce Financial Services Cloud, unstructured document extraction at scale, or Azure Purview.