# 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.

I am working on a system using AI to review and respond on Google Drive (Shared Drive) folders of PDF's. Using Gemini as a POC I get responses that sometimes reach outside of my specified folders of content, but sometimes, some PDF files are ignored too. Also, when the response to a prompt come back, the sources are linked. However, the links only bring up the first page of the PDF file wherein the linked source material is, AND NOT THE pdf PAGE of the specific info. I need to have the AI (Gemini, Grok, etc.,) be used to query just.... but all, of the PDF files, within a set of folders in Google Drive (Shared Drive), and to respond with linked content. Said links must open to the PDF PAGE, not just the PDF which houses the specific info. In short, I think I need a viewer, but someone who has experience working with AI and PDF's will likely know the issue I am running into. In the end my system will have a UI attached, so there is a lot of possible side work on this project. First I need to build a better POC. For instance, if I open ONE of the PDF files in Google Drive, I can prompt on that file, and the correct PDF page does come up in the viewer, (While no other files are considered for the queried content.) But when I give Gemini many source PDF's or a folder of PDF's, the links only go to the first page pf the PDF with the information used as the sourcwe.

We are building a HIPAA-compliant SaaS platform for medication stewardship in skilled nursing facilities (SNFs). The platform allows clinical pharmacy consultants and providers to upload scanned medical documents, run AI-powered medication and disease state reviews, and generate clinical findings — all without storing any patient data. This is a focused, well-defined MVP. No scope creep. We need a developer who moves fast, communicates clearly, and has real experience with HIPAA-eligible AWS architecture. Core concept — stateless processing: This platform is intentionally stateless. Documents are uploaded, processed through OCR, analyzed by AI, and the findings are displayed to the user. Nothing is written to a database. No patient data or documents are retained after the session ends. The platform processes PHI transiently and discards it — significantly simplifying the HIPAA footprint while maintaining compliance. What you will build: 1. AWS infrastructure (HIPAA-eligible, stateless) — S3 used only as a temporary processing buffer (files deleted immediately after OCR completes) — AWS Textract for OCR processing of scanned PDFs and images — AWS Bedrock (Claude Sonnet) for AI-powered clinical analysis — AWS Cognito for user authentication only (no clinical data stored) — AWS Amplify or CloudFront for React frontend hosting — KMS encryption for data in transit — All services configured under AWS BAA coverage — No RDS or persistent database required for clinical data 2. React frontend — Clean single-page application — Document upload UI (drag/drop, supports PDF and image files) — OCR text display with basic edit capability before analysis — Free-text question input (user asks Claude questions about the document) — Claude response display panel — Copy to clipboard button on all output — User login and profile page (name, email, facility) — Membership and billing settings page — Stripe monthly subscription integration 3. HIPAA compliance — Stateless architecture — no PHI persisted after session — HTTPS enforced on all endpoints — AWS BAA signed and covering all services — User BAA acknowledgment on signup — Audit logging for access events — Privacy policy and terms of service integration What we are NOT building in this phase: — Mobile app — EHR or PointClickCare integration — Stored intervention history or dashboard — Cost savings calculator — Admin panel — Anything beyond the three core features above: upload, analyze, copy output Ideal candidate: — 3+ years React and AWS experience — Prior HIPAA-eligible AWS builds — please describe your specific experience in your proposal — Hands-on experience with AWS Textract or comparable OCR pipelines — Familiarity with AWS Bedrock or direct LLM API integrations — Experience with stateless or ephemeral data processing architectures — Stripe subscription integration experience — Strong communicator — weekly video check-ins required — Available to start within 2-4 weeks Engagement details: — Estimated scope: 40–60 hours — Timeline: 8–10 weeks — Budget: $2,500–$4,500 USD fixed price preferred — Payment milestones: 25% upfront, 25% at working OCR pipeline, 25% at working Claude integration, 25% at launch — Communication: Weekly video check-in + async messaging How to apply: In your proposal please answer these four questions specifically: 1. Describe a HIPAA-eligible AWS application you have built — what services did you use and how did you handle PHI? 2. Have you implemented stateless or ephemeral document processing before? How did you approach it? 3. What is your experience with AWS Textract or other OCR pipelines? 4. How would you integrate AWS Bedrock or a Claude API call into a React frontend securely? Proposals that do not answer these four questions will not be considered. About us: We are an early-stage clinical SaaS platform founded by a Clinical Pharmacy Specialist. We are building a tool that genuinely improves patient care and safety in long-term care settings. We want a developer who takes pride in clean, secure, well-documented code and wants to be part of building something meaningful in healthcare. If that is you, we would love to hear from you.

We have an existing application that includes several AI-powered features and integrations. Some features are currently not functioning as expected, and we are looking for an experienced developer to review the codebase, identify the root causes, and implement reliable fixes. The ideal candidate should be comfortable working with AI/LLM integrations, debugging complex systems, and improving existing functionality without disrupting the overall application.

We are an investment firm with a portfolio of healthcare companies. We are seeking to begin building our data capture systems across our business and layer AI to surface summarize and store insights. This is a process that is in parallel to our operations team SOP'ing our process in anticipation of expansion. It is our opinion that we have a relatively simple business process from end to end and lots of potential to capture useful data signals across each department/function. We have drafted a rough business process / data ontology diagram showing our preferred approach. We are seeking an expert to: 1 ) Create lightweight data systems to capture data signals from end to end across our business (Recruiting to Onboarding to Scheduling to Payroll to Finance to Legal to). This also includes organizing and categorizing our past / existing data in addition to capturing signals for future data. 2 ) Layer AI / agentic AI automations that can surface insights, categorize and aggregate info, populate knowledge databases, etc. Example Data Signals / Use Cases: Fireflies recorded meetings Tagging emails in inbox as Legal/Finance/Scheduling/Onboarding etc Job Board Postings Airtable (For building a lightweight scheduling/employee management system) (For storing a knowledge database and rolodex) To Apply: Please briefly present an instance of implementing a similar lightweight solution to capture data signals and convert the data into meaningful and actionable insight via AI

We are a small residential real estate investment company seeking an AI Solutions Architect to enhance our acquisition platform. The role involves designing and implementing AI solutions to improve data analysis and decision-making processes. The ideal candidate will have experience in AI architecture and a strong understanding of real estate data analysis.

We're a small SaaS company and we have a CSV dataset (~10,000 rows) of customer activity data including features like subscription length, login frequency, support tickets filed, monthly spend, and whether the customer churned (binary label). We need someone to build a simple but effective churn prediction model and expose it via a lightweight API so our internal tools can call it. Scope of work: - Perform basic exploratory data analysis (EDA) and generate a few key visualizations (churn distribution, feature correlations, top predictive features) - Clean and preprocess the data (handle missing values, encode categoricals, scale features) - Train and evaluate at least 2-3 classification models (e.g., Logistic Regression, Random Forest, XGBoost) with appropriate metrics (accuracy, precision, recall, F1, AUC-ROC) - Select the best model and save it as a serialized file (pickle or joblib) - Build a simple FastAPI endpoint that accepts customer features as JSON input and returns a churn probability score - Provide a Jupyter notebook with the full EDA + modeling workflow, plus the FastAPI app code - Include a brief README with setup instructions Deliverables: GitHub repo or zip with notebook, model file, API code, requirements.txt, and README. We're looking for someone who can do this quickly and cleanly — no over-engineering needed, just solid ML fundamentals and a working API. Ideally completed within a couple of days.

We are looking for an experienced full-stack developer with strong AI-assisted development skills to help us transform our existing payment administration web platform into a modern application. We operate a payment management/admin system and want to accelerate development using AI tools such as Cursor, Claude, ChatGPT, GitHub Copilot, or similar technologies. The goal is to rapidly build, improve, and scale our payment administration platform while maintaining high code quality and security standards.

We are looking for a Senior AWS Engineer who can start immediately and help with an urgent AWS-related task for a financial technology project. The AWS environment supports sensitive financial workflows, data, and application services, so security, reliability, and production-grade troubleshooting are critical. The expected timeline is 5–10 hours, so we need someone highly experienced, fast, and able to work independently with minimal guidance.

26ers is building Human + AI operating systems that help organizations improve decision quality, execution speed, and organizational leverage. We are seeking a customer-facing AI Architect who can work directly with executives, operational leaders, and technical teams to design practical AI solutions that solve real business problems. This role helps organizations identify high-value AI opportunities, redesign workflows, modernize operations, and implement Human + AI operating systems that improve execution, decision-making, and organizational effectiveness. The ideal candidate can move fluidly between customer conversations, workflow discovery, solution design, governance considerations, and implementation planning. Responsibilities • Participate in customer discovery and solution design conversations • Analyze current-state workflows and identify AI transformation opportunities • Design Human + AI operating models, agentic workflows, and operational systems that improve execution and decision-making • Create solution blueprints, implementation plans, and statements of work • Collaborate with implementation developers and technical delivery teams • Consider data governance, security, compliance, and operational requirements throughout solution design • Contribute to the development of reusable 26ers methodologies, frameworks, and institutional knowledge • Design systems that capture, structure, and operationalize organizational knowledge and institutional learning Ideal Experience • Experience designing AI-powered business workflows and operational systems • Strong understanding of OpenAI, Claude, and modern LLM-based solution design • Experience with workflow orchestration platforms, AI agents, automation systems, and API-based architectures • Strong understanding of data governance, information security, and enterprise AI deployment considerations • Experience translating business requirements into solution architectures, implementation plans, and statements of work • Customer-facing experience in consulting, solution engineering, professional services, digital transformation, or technical advisory roles • Experience conducting discovery workshops, workflow assessments, and current-state/future-state design exercises • Understanding of operating model design, workflow modernization, and organizational transformation • Strong written and verbal communication skills with executive stakeholders • Ability to leverage AI tools to rapidly produce architecture drafts, blueprints, requirements documents, implementation plans, training materials, and customer deliverables Nice to Have • Experience with Gemini, MCP, LangGraph, CrewAI, AutoGen, or similar orchestration frameworks • Experience with n8n, Make, Zapier, or workflow automation platforms • Experience with vector databases, RAG architectures, and organizational knowledge systems • Experience building or deploying multi-agent systems • Government, healthcare, financial services, or other regulated industry experience • Startup, founder, or early-stage company experience • Experience designing systems that capture institutional knowledge, operational learning, or organizational intelligence • Military, consulting, enterprise software, or transformation leadership experience Success in this role • Quickly understand a client's operating environment, workflows, and business objectives • Identify high-value opportunities for AI-enabled transformation and operational leverage • Translate customer goals into practical solution designs, implementation plans, and delivery roadmaps • Balance innovation, governance, security, and operational realities • Help organizations move from AI experimentation to operational execution This role may begin on a contract basis and expand into a longer-term strategic partnership as 26ers grows.