Welcome to my home on the Internet!

I'm a software engineer based in New York, interested in ML, distributed systems, and compilers.

Building a high recall vector database serving 1 billion embeddings from a single machine
From 3 TB RAM to 96 GB: superseding billion vector HNSW with 40x cheaper DiskANN
From Kevin Bacon to HNSW: the intuition behind semantic search and vector databases
Exploring Hacker News by mapping and analyzing 40 million posts and comments
Building a web search engine from scratch in two months with 3 billion neural embeddings