Research Associate – Department of Cancer and Genomic Sciences – 107471 – Grade 6 Part-time

Job Title

Research Associate

Job Description

Department of Cancer and Genomic Sciences, School of Medical Sciences, College of Medicine and Health

Location: University of Birmingham, Edgbaston, Birmingham UK

Full time starting salary is normally in the range £33,002 to £35,608 with potential progression once in post to £39,906

Grade: 6

Part Time (0.25 FTE), Fixed Term contract up to March 2027

Closing date: 26th May 2026

This post supports the NIHR BRC-funded study TRANsCEnD-CPRD: Validation of a Foundation Model for diabetes and multimorbidity (Diabetes2Vec) using real-world primary care data, which focuses on the validation and fairness evaluation of a transformer-based AI model for predicting individual diabetes progression and treatment outcomes in UK primary care populations.

The post holder will be based within the Department of Cancer and Genomic Sciences (CGS) and will join the Centre for Health Data Science, working under the supervision of Dr Andreas Karwath and in close collaboration with the co-investigators, Professor Nicola Adderley (BRC Data Theme Deputy Lead) and Dr Chris Sainsbury, as well as the project collaborator, Dr Feng Dong (University of Strathclyde). The role will provide technical and analytical support for the adaptation of existing model code to the CPRD environment, the validation of the Diabetes2Vec model on nationally representative primary care data, and the systematic audit of model performance across ethnic minority groups. The post will focus primarily on computational analysis, data transformation, and equity evaluation within a trusted research environment.

The TRANsCEnD-CPRD team are seeking an individual with a degree or equivalent in Health Data Science, Computer Science, Artificial Intelligence, or a closely related discipline relevant to clinical predictive modelling and fairness in machine learning, who has practical experience in its application using established tools (for example, NumPy, Pandas, scikit-learn, PyTorch, or TensorFlow) and procedures. Experience working with electronic health records or primary care data, and in preparing, structuring, and analysing large-scale longitudinal datasets, is desirable.

The anticipated start date is June 2026. The post will be offered on a hybrid working basis, with an expectation of at least three days per week in the office.

The Research Associate role is a fixed-term post working within the defined NIHR BRC-funded research project focused on the validation of a transformer-based foundation model (Diabetes2Vec) for diabetes and multimorbidity using real-world primary care data from CPRD Aurum, linked to Hospital Episode Statistics Admitted Patient Care (HES APC). You will apply skills in health data science, sequence modelling, and clinical AI evaluation to support data transformation, model validation, and fairness audit activities within a trusted research environment (DEXTER). You will also carry out predefined model performance analyses and equity assessments across defined population subgroups, under the direction of senior researchers.

The Research Associate will be expected to prepare, structure, and quality-check CPRD primary care data, including the generation of clinical event tokens and cohort definitions aligned with established project protocols and BRC standards. You will also be expected to provide technical and analytical support within a multidisciplinary team to support agreed project objectives, and contribute to the reporting of research outputs, including reports, conference presentations, and publications. As part of the role, you will use and maintain computational pipelines, tokenisation workflows, and version-controlled codebases to support reproducible analyses, and will contribute to the preparation of preliminary data supporting a subsequent large-scale NIHR or MRC grant submission.

The University of Birmingham is committed to creating a more sustainable university and world. The Department of Cancer and Genomic Sciences and the Centre for Health Data Science are dedicated to minimising our environmental impact, promoting social responsibility, and fostering a diverse and inclusive workplace. We are working towards environmentally responsible practices and team members are expected to contribute towards achieving these goals.

Main Duties

• Collect research data; this may be through a variety of research methods, including but not limited to Dexter, CPRD, scientific experimentation, literature reviews, and research interviews.
• Analyse research data as directed.
• Develop or adapt techniques, models and methods.
• Present research outputs, including drafting academic publications or parts thereof, for example at seminars and as posters.
• Provide guidance as required to support staff and any students who may be assisting with research.
• Deal with problems that may affect the achievement of research objectives and deadlines.
• Carry out administrative tasks related directly to the delivery of the research.
• Promotes equality and values diversity acting as a role model and fostering an inclusive working culture.

Person Specification

• Degree or equivalent in relevant subject area.
• Practical experience of applying the relevant skills and techniques.
• Ability to analyse information and communicate effectively in written and verbal form within a multi-disciplinary team.
• Ability to access and organise resources successfully, with the ability to plan and prioritise tasks to meet agreed deadlines.
• Knowledge of the protected characteristics of the Equality Act 2010, and how to actively ensure in day-to-day activity in own area that those with protected characteristics are treated equally and fairly.