Experience
Over 10 years in health research data across Tanzania and sub-Saharan Africa
Research Data Scientist
- Build reproducible ETL pipelines that harmonise multi-country spatial datasets (facility locations, population, service availability).
- Run travel-time and flood-impact accessibility modelling using friction surfaces, road networks and flood hazard layers.
- Develop Shiny dashboards and Quarto portals for National Malaria Control Programmes.
- Lead the Data Engineering Team and train early career researchers.
Data Analyst Consultant
- Managed and analysed spirometry and respiratory quality-of-life data for a study of respiratory dysfunction in people with and without HIV.
National Data Analyst, WHO EMOTIVE Project
- Built REDCap databases and a monitoring dashboard for a multi-country trial.
- Wrote a data-handling SOP adopted by five countries; trained 56 research nurses.
Research Scientist Intern, SHLC Project
- Analysed regional non-communicable disease trends in R and Stata; built Tableau visualisations and co-authored reports.
Data Manager
- Configured GPS devices and managed household geolocation data collection, followed by spatial cleaning, mapping and exploratory analysis.
- Built validated trial databases (OpenClinica, REDCap, ODK), reaching 98% data integrity and over 97% participant retention.
Tutor
- Taught computing mathematics, programming and systems analysis and design.
Skills
Programming: R (advanced), Python, SQL, Stata
Geospatial: terra, sf, QGIS, Google Earth Engine, travel-time modelling, GraphHopper and OSRM routing, flood hazard analysis
Data engineering: ETL design, DuckDB, GeoParquet, GitHub Actions, REDCap, ODK
Visualisation: Shiny, Quarto, ggplot2, Tableau
Professional training
- Advanced Course in Epidemiological Analysis, LSHTM (2023), funded by an HIV Research Trust Scholarship
- Survey Methodology and Data Management, GESIS / MRC Uganda (2022)
- Using Stata for Health Research, MRC/UVRI and LSHTM Uganda (2019)