Resume
Yeqiu (Jason) He — AI Systems Engineer: agentic systems, RAG, LLM integration.
Summary
I design, ship and operate production LLM systems end-to-end — multi-agent orchestration, retrieval-augmented generation and Model Context Protocol — owning the full lifecycle from architecture through deployment to live operation on self-hosted infrastructure. I grew into AI engineering from 5+ years shipping enterprise process automation (70–90% manual-processing reduction across 30+ enterprise systems), then rebuilt that same systems-engineering and evaluation discipline around LLMs.
Selected work
- OpenClaw — a fleet of 8 specialised agents in continuous production: custom inter-agent bus protocol, persistent anchor-based memory with hybrid semantic retrieval, multi-provider LLM routing with fallback.
- Meinrag — multimodal RAG platform serving a 3,300+ document legal corpus in production: hybrid retrieval (BM25 + dense, RRF) with LLM re-ranking and PDF bounding-box citations — every claim traceable to source.
- Five more open-source builds — music discovery, game platforms, language tools — each documented on the technical blog and YouTube.
Skills
- AI / ML
- LLM integration & orchestration (Claude, OpenAI, Codex) · RAG (FAISS, embeddings, re-ranking, hybrid BM25/dense) · MCP servers · multi-agent systems · model calibration & evaluation · vector search · Monte Carlo simulation
- Programming
- Python · TypeScript / JavaScript · C# · VB.NET · SQL · Fortran
- Backend / Data
- FastAPI · SQLAlchemy · PostgreSQL · MySQL · SQLite · ETL / data-pipeline design · REST APIs
- Automation
- UiPath · PowerShell · Windows automation · process optimisation
- Infrastructure
- Docker · Linux · Git · self-hosted ops (Raspberry Pi / NAS / VPS)
- Frontend
- Vue.js · React · Nuxt · Tailwind · Astro
Languages
English (full professional proficiency) · Mandarin Chinese (native) · German (basic)
The full résumé — contact details, work rights and availability — goes out privately per application. Reach me via GitHub.