Selected work
Production-style systems, not demos — each entry leads with the outcome, and every number is labeled measured or estimated.
An agentic retrieval system over a large enterprise technical-documentation corpus that measurably cut specification-research time — built self-initiated, now adopted by colleagues.
A modular, offline-capable multi-agent platform — OpenAI-compatible gateway, control plane, autonomy engine, RAG, and IDE integration — with a five-mode adversarial peer-review loop and zero hosted-LLM dependency.
A self-built two-node multi-GPU cluster serving local models with a privacy-first architecture, thermal-aware autonomy, and GPU-wedge diagnosis and recovery.
A multi-source job aggregator with a "truth gate" for LLM résumé and cover tailoring that blocks unsupported claims — grounded in an evidence bank.