Sr Data Engineer with 15+ years building systems at the intersection of data, ML, and privacy. I hold a patent in PII anonymization, and have a habit of cutting compute costs by absurd percentages.
See my work → View CVOffline code context retrieval for LLMs. Indexes a repository and answers natural-language queries with a minimal, high-signal context pack.
Month-over-month drift monitoring across very large datasets, with a dashboard layer for spotting anomalies before they reach downstream consumers.
A control center for unified third-party data — one place to see what arrived, what passed, and what moved.
SQL-first data quality gating. Runs table, column, and row-level checks and blocks bad data from promoting downstream.