At NatWest Group, I led the migration of a 10+ TB time-series database from on-premises SQL Server to GCP PostgreSQL. I also developed a natural-language query agent that unified information from more than 10 enterprise datasets and reduced retrieval time from two days to about two minutes.
I’ve engineered PySpark pipelines for cloud data migrations and built a RAG pipeline for enterprise document search. In personal projects, I built a document extraction system deployed as a production REST API and an end-to-end data platform for ingestion, transformation, and analytics.

