AI/ML engineer and applied researcher building agent frameworks, RAG systems, and ML infrastructure. I ship open-source used in production by teams at MongoDB and LINE. MCS student at UIUC.
- trustgraph: I built much of the retrieval and multimodal stack in this RAG and agent framework: cross-encoder reranking, hybrid retrieval (BM25 + vector with RRF fusion), inline source attribution for RAG answers, and a pluggable image-to-text service for vision models.
- comprisk: competing-risks survival analysis for Python, and my first-author research (arXiv:2607.09431). Includes the only native-Python competing-risks random survival forest, bit-identical to R's randomForestSRC and 10-22x faster.
- js-toml: TOML parser and serializer for JavaScript. 16k+ weekly downloads with 4.3x year-over-year growth, TOML 1.1, passes the official toml-test compliance suite. Used by 380+ projects, including MongoDB's docs platform and LINE's user feedback product.
- AgentQuant: open-source AI agent platform that turns natural-language trading ideas into quantitative backtests. Top 3 at the NVIDIA AI Hackathon, 2025. Built at NLPQuant, the AI studio I founded.
- Led Mogara, the organization behind QSanguosha, an open-source implementation of the Sanguosha board game with millions of downloads; its Lua API supported a community of 1000+ mod creators.