- Healthcare data pipelines — PySpark, Databricks, R/dbplyr, SQL
- National Secure Data Environemnts - NHS England Secure Data Environment, SAIL in Wales.
- LLM applications — RAG systems for clinical documentation and codebase intelligence
- Data curation tools — phenotype search, metadata management, validation frameworks
- Research software engineering — making analytical code reproducible and shareable
- Custom Tool Development I build tools and pipelines for cardiovascular and cancer research using large-scale data.
- 📊 Cardiovascular and Oncology datasets for world leading reseach.
- 🤖 Question-answering systems for healthcare documentation.



