About
I'm CS at the University of Washington. I spend most of my time thinking about how AI agents remember, reason, and communicate — and building the infrastructure that makes that possible.
Previously researched privacy-preserving vector search at UW's HPDIC Lab. Currently founding engineer at Agentnomics, and interned at UKG and Toyota Racing Development.
Work
Engram→
Hybrid memory layer for AI agents combining knowledge graph traversal, vector search, and temporal awareness into a single retrieval system.
TokenRouter→
TokenRouter routes LLM requests to the cheapest adequate model using real-time difficulty classification and semantic caching — achieving 68% cost reduction at 94% quality parity.
Lookout→
Distributed multi-camera video RAG with on-device multimodal embeddings over peer-to-peer QUIC. Built in 24 hours — took Grand Prize, Best B2B, and Best Technical Hack at the Cactus × DeepMind × YC hackathon, earning a guaranteed YC interview.