Writing

Notes on the parts of a system that explain why it works the way it does, search, AI personalization, backend infrastructure, and the trade-offs underneath.

300ms Semantic Search on a Candidate Listing Page Jul 2026

Vector search over hundreds of thousands of candidates is fast, a steady 10 to 30ms. The latency that threatens a search page lives in everything around it. Here's how the...
Building a Cost-Effective Vector Embedding Sync Pipeline for Semantic Search Jul 2026

The expensive part of a vector sync pipeline is almost never the embedding call. It's how often you make it, and how often you didn't need to.