AI Full Stack Engineer | RAG, AI Agents & Python

Job Description We’re looking for an experienced AI Full Stack Engineer to help us build and improve an AI-powered web application. The project involves developing LLM-powered features, RAG pipelines, AI agents, and backend services, with a focus on building reliable and production-ready AI functionality. You’ll work across the AI and full-stack layers, including backend development, AI integrations, data retrieval, and frontend features. Responsibilities Build and integrate AI agents and LLM-powered features Develop RAG pipelines and AI knowledge bases Work with OpenAI, Claude, or similar LLM APIs Build backend services and APIs using Python/FastAPI Implement document ingestion, embeddings, vector search, and retrieval Integrate third-party APIs and external services Develop or improve frontend features using React/Next.js Optimize AI responses, workflows, reliability, and performance Debug and improve existing AI/full-stack functionality Deploy and maintain production-ready applications Requirements Strong experience with Python and FastAPI Experience building RAG/LLM applications Understanding of embeddings, vector databases, and retrieval pipelines Experience with AI agents / agentic workflows Experience with OpenAI, Claude, LangChain, or similar technologies Strong API integration experience Experience with React.js or Next.js PostgreSQL or MongoDB experience Familiarity with Docker and AWS Ability to work with an existing codebase and take ownership of features Nice to Have n8n, Make, or Zapier experience Experience building AI SaaS products Experience with chatbots or AI assistants Experience with production AI systems and LLM optimization Hourly Rate: $25–$40/hr Project Type: Hourly — potentially long-term Experience Level: Intermediate to Expert Length More Than 6 months