Full Stack AI Engineer – LLM Apps, RAG & API Integrations (Python/React)

We're looking for a Full Stack AI Engineer to design, build, and ship production-grade applications that combine modern web development with AI/LLM integration. You'll work across the stack from backend APIs and data pipelines to frontend interfaces building features powered by large language models, retrieval-augmented generation (RAG), and AI agents. Responsibilities: - Design and build full-stack web applications (backend + frontend) - Integrate LLM APIs (OpenAI, Anthropic, Gemini, etc.) into product features - Build and optimize RAG pipelines (vector databases, embeddings, chunking strategies) - Develop AI agents/workflows using frameworks like LangChain, LangGraph, or similar - Design clean, scalable REST/GraphQL APIs - Build responsive frontend interfaces (React/Next.js or similar) - Work with databases (PostgreSQL, MongoDB, vector stores) and cloud infra (AWS/GCP) - Write clean, maintainable, well-documented code - Collaborate on architecture decisions and technical planning Requirements: - Strong experience with Python (FastAPI/Django/Flask) and JavaScript/TypeScript - Hands-on experience with LLM integration (OpenAI, Anthropic, or open-source models) - Experience building RAG systems (pgvector, Pinecone, MongoDB Atlas, etc.) - Familiarity with agent frameworks (LangChain, LangGraph, CrewAI, or similar) - Frontend experience with React/Next.js - Experience with cloud deployment (AWS, GCP, Azure) and Docker - Strong understanding of API design and database modeling - Ability to work independently and communicate clearly Nice to have: - Experience with voice AI (VAPI, Twilio, Deepgram, ElevenLabs) - Experience with multi-tenant SaaS architecture - Background in production ML/AI systems, not just prototypes To apply: Please share relevant past projects (links/repos preferred), your typical stack, and your availability/timezone overlap.