AI Developer

AI Full-Stack Engineer Needed for Existing SaaS – FastAPI / TypeScript / LLM Integration We have an existing, fully operational SaaS application and are looking for an experienced AI Full-Stack Engineer to improve, optimize, and expand the AI capabilities within the platform. This is not a build-from-scratch project. The application is already live and has an established architecture, backend, database, and frontend. We need someone who can quickly understand an existing codebase and implement new AI functionality without unnecessarily rebuilding working components. Tech Stack * Python / FastAPI * TypeScript * Next.js / React * PostgreSQL * REST APIs / WebSockets * Redis * Vector databases such as Pinecone, Qdrant, Weaviate, or pgvector * AI/LLM APIs such as OpenAI, Anthropic Claude, Google Gemini, or similar Responsibilities * Review and understand our existing application architecture and codebase * Develop new AI-powered features within the existing product * Build and maintain Python/FastAPI services for AI workflows * Integrate AI functionality with our TypeScript/Next.js application * Design reliable LLM workflows and structured outputs * Implement RAG, embeddings, semantic search, and document retrieval where required * Develop tool/function calling and agent-based workflows * Improve prompts and overall AI response quality * Implement validation, retries, fallbacks, and error handling for LLM responses * Optimize AI API usage for latency, reliability, and cost * Troubleshoot and improve existing AI functionality * Work with PostgreSQL, Redis, vector databases, and external APIs * Maintain clean, scalable, well-documented, production-ready code Ideal Candidate * Strong Python experience, particularly with FastAPI * Strong TypeScript / JavaScript experience * Experience with React and/or Next.js * Proven experience building AI features for real production applications * Strong understanding of REST APIs and backend architecture * Experience with OpenAI, Claude, Gemini, or other major LLM providers * Experience with structured outputs, function/tool calling, and prompt engineering * Practical knowledge of RAG pipelines, embeddings, chunking, retrieval, and vector databases * Familiarity with AI agents and multi-step LLM workflows * Experience implementing logging, monitoring, and evaluation for AI systems * Understanding of token usage, caching, latency, and LLM cost optimization * Comfortable joining and improving an established codebase * Able to work independently, troubleshoot problems, and communicate clearly Bonus Experience Experience with any of the following would be a plus: * LangChain / LangGraph / LlamaIndex * pgvector / Pinecone / Qdrant / Weaviate * AI agent architectures * Background jobs and queues * Docker / AWS / GCP * LLM evaluation and observability * Streaming AI responses * Speech-to-text / text-to-speech APIs * Multimodal AI (text, images, audio, or documents) When Applying, Please Include 1. Examples of AI-powered applications you have worked on 2. Your experience with Python/FastAPI and TypeScript/Next.js 3. Which LLM APIs and AI frameworks you have used 4. Your experience with RAG, vector databases, and AI agents 5. Your specific role in previous AI projects 6. Links to relevant projects, GitHub repositories, or portfolio examples if available 7. Your current availability 8. Your hourly rate or estimated project rate Important: We are specifically looking for someone who is comfortable working with an existing, functioning product. We do not want the application rebuilt from scratch unless there is a clear technical reason for a particular component to be replaced. We are looking for someone practical who can understand what is already working, identify areas for improvement, and implement reliable AI functionality efficiently. There is strong potential for ongoing/long-term work if the initial project is successful.