Jonathan Lee

I’m a senior full-stack AI engineer with 9+ years architecting and delivering production-scale AI applications and cloud-native platforms. I focus on Generative AI, Retrieval-Augmented Generation (RAG), and LLM orchestration, turning complex systems into reliable, high-impact solutions.

In my most recent role, I built and deployed an enterprise Generative AI platform on AWS Bedrock using Python to enable secure RAG workflows and knowledge discovery. I implemented document ingestion pipelines (parse, chunk, embed, index) and created monitoring dashboards and alerts to track RAG accuracy, hallucination rates, relevance, and latency across releases.

I also own end-to-end product execution, including building user-friendly RAG UIs with React, Next.js, and TypeScript—adding conversational experiences, citations, and feedback mechanisms to improve trust and adoption. Earlier, I shipped cross-platform meeting intelligence products using React, Electron.js, React Native, and Node.js, and built a Python RAG pipeline with OpenAI Embeddings, Pinecone, and LangChain, reducing LLM inference costs by 15% through intelligent model routing and prompt optimization.

Before that, I developed interactive collaboration and AI workflow generation for an “infinite canvas” experience, including real-time multiplayer features with WebSockets and Redis pub/sub and AI-powered workflow generation using OpenAI models and LangChain. I’ve also delivered enterprise web applications and predictive analytics models in earlier roles, using modern frontend and backend stacks and cloud deployments to support business-critical outcomes.