LLM serving · RAG · agent systems
Wuxi, China
I build and operate production LLM / RAG / agent stacks — self-hosted Dify ops, retrieval pipelines, and upstream bugfixes in active AI repos.
Upstream contributions to systems interviewers recognize (Dify and related LLM / RAG / agent stacks), with reproducible fixes and tests — not drive-by docs.
Python · TypeScript · vLLM · Dify · RAGFlow · Milvus · Docker



