Description
We’re looking for an experienced full-stack developer or small agency to help us build and iterate on an AI-powered application. The core of the work is integrating large language models (LLMs) into a production web app, with a Python/FastAPI backend and a Next.js frontend. What you’ll be working on: Designing and building LLM-powered features (chat, summarization, structured data extraction, agentic workflows, etc.) Integrating the Claude AI / Anthropic API (and other LLM providers as needed) Building and maintaining REST APIs with FastAPI Developing the frontend in Next.js / React / TypeScript Prompt engineering, streaming responses, and optimizing for latency and cost Nice to have: RAG pipelines, embeddings, and vector databases Tech stack: Python, FastAPI Next.js, React, TypeScript LLMs — Claude AI / Anthropic API (plus OpenAI or others) Bonus: LangChain/LlamaIndex, vector DBs (Pinecone, pgvector), Docker, cloud deployment What we’re looking for: A strong track record shipping AI/LLM applications end to end Clean, well-documented code and clear, proactive communication Comfortable working independently and proposing solutions Some overlap with BST hours for occasional syncs