Data Scientist – Health Outcomes for UK Biobank

About the role

We are seeking a Data Scientist to lead the design, development and evaluation of processes that transform UK Biobank health and lifestyle data into standardized data models, focusing on the OMOP model. The role involves close collaboration with data engineers and research partners to build, maintain and improve ETL pipelines, ensuring datasets are validated and ready for research.

Key responsibilities

• Design and develop processes for converting UK Biobank data into OMOP‑standardized models.
• Collaborate with data engineers to implement, maintain and enhance OMOP ETL pipelines.
• Validate transformed datasets to ensure they are research‑ready.
• Provide scientific leadership in data transformation and modelling activities.

Required profile

• Higher degree (MSc or PhD) in epidemiology, data science, statistics, computer science, health informatics or a related discipline.
• Strong understanding of linked electronic health records and experience using them in epidemiological or population‑health research.
• Proven experience analysing large, complex health datasets.

Required skills

• Statistical/programming software: R, Stata, SAS, Python, SQL.
• Knowledge of the OMOP common data model and ETL processes.

What we offer

• Work within Oxford Population Health, a multidisciplinary research environment.
• Opportunity to contribute to high‑impact research on disease causes, prevention and treatment.