Building pipelines
that hold up.

I'm a London-based data professional with a First Class BSc in Data Science & Computing from Birkbeck, University of London. Studying part-time while building real-world projects shaped how I approach engineering: deliberately, methodically, and with a strong bias for systems that hold up under pressure.

My work is grounded in data engineering and analytics engineering — building pipelines and systems that are reliable, observable, and produce data that people can trust and act on. I specialise in the full pipeline lifecycle: from raw ingestion and orchestration (Airflow, CDC with Debezium/Redpanda) to transformation and warehousing (dbt, DuckDB, BigQuery), data quality enforcement (Great Expectations), and lineage tracking (OpenLineage).

On the data science side, I apply machine learning where there's genuine predictive value: financial time-series forecasting with LSTM networks, statistical modelling, and rigorous model evaluation. I treat ML as an engineering discipline — reproducible workflows, honest backtesting, and results you can stand behind.

I work across finance, sport, and urban/environmental data — domains where the stakes of data quality and pipeline reliability actually matter. My projects span TfL real-time data, Premier League and F1 analytics warehouses, London air quality monitoring, and equity price forecasting.