Zhen Ee
I'm a backend engineer building AI systems. Most of my career has been on distributed services and proxy infrastructure; the last stretch has been going deep on local LLM inference, RAG retrieval, and computer vision.
//currently (August 2026): the EU AI Footprint Scanner is live — a GitHub App selling via Lemon Squeezy under Argus Intelligence. Day-job build is a self-learning proxy debugger — HAR diff plus LLM/RAG that drafts config patches and validates them. More on /now.
Selected projects
all →- EU AI Footprint ScannerAI/ML · Tools
AST-based static analysis for AI/ML library use in Python codebases, shipped end-to-end as a paid GitHub App — scanner engine, Cloudflare Worker + Container webhook pipeline, KV entitlement gate, and Lemon Squeezy billing.
- Self-learning proxy debuggerAI/ML · Systems
A closed-loop debugging system for the proxy platform — YOLO visual + functional QA gate, blue-green deploys with instant rollback, LLM + RAG on the novel-fix path, event-driven staleness tracking so learned fixes don't rot, and a Telegram approval loop for anything complex.
- Edge routing proxyBackend · Systems
A multi-layer reverse proxy for upstream-resilient routing — OpenResty, Couchbase, and a TypeScript control plane. Serves ~10M requests/day in production from a 2 vCPU / 2 GB node.
10M req/day in production · 2 vCPU GCP e2-small · 60k concurrent at 100% in load test
- aegis-ragAI/ML
A modular RAG framework for benchmarking retrieval strategies — vector vs. keyword, with and without rerankers — before anything touches an LLM.
- Local LLM orchestration and benchmarkingAI/ML · Systems
Running open-weight models locally via llama.cpp — from what fits on a 16GB MacBook Pro to quantizing a 72B on a 256GB Mac Studio, and measuring what the compression actually costs.
72B Q6_K vs f16: quality within noise (+0.0057 PPL), decode 2× faster (10.1 vs 5.1 t/s) · Qwen 4B at ~50 TPS on 16GB