Postdoctoral Researcher in Artificial Intelligence for Robust Clinical Prediction Modelling

University of Oxford; Oxford; On-site; GBP 30,000 - 40,000; Full time

Job summary

A prestigious university in Oxford invites applications for a Postdoctoral Researcher in machine learning. The role involves developing AI methods for clinical prediction models, contributing to publications and software development. Candidates should have a PhD or be near completion in a quantitative discipline and possess strong programming and machine learning skills. This full-time, fixed-term position is available from January 2026 and offers flexible working arrangements.

Qualifications

• PhD or nearing completion in computer science, mathematics, statistics, engineering, or a related field.
• Essential experience in machine learning or statistical modelling.
• Advantageous experience with healthcare data and deep learning.

Responsibilities

• Contribute to high-impact publications.
• Involved in open-source software development.
• Assist in creating training materials.

Skills

Strong programming skills

Experience in machine learning

Statistical modelling experience

Experience with healthcare data

Knowledge of algorithmic fairness

Deep learning for biomedical data

Education

PhD in quantitative discipline

Job description

Nuffield Department of Women's & Reproductive Health, Big Data Institute, Li Ka Shing Centre for Health Information and Discovery, Old Road Campus, Oxford OX3 7LF

We invite applications for a Postdoctoral Researcher to join the research group of Professor Christopher Yau (cwcyau.github.io) at the Big Data Institute, University of Oxford. This post will contribute to the development of a new simulation-based pre-training framework for building more robust and trustworthy machine learning-based clinical prediction models.

Funded by the Medical Research Council (MRC) and the National Institute for Health and Care Research (NIHR), the project aims to advance artificial intelligence (AI) methods that improve the reliability of clinical prediction models when faced with data drift, bias, and fairness challenges. The research will involve developing deep learning and synthetic data generation approaches and applying them to exemplar studies in ovarian cancer prognosis, COVID-19 prediction, and childhood mental health.

Requirements: You will have (or be close to completing) a PhD in a quantitative discipline such as computer science, mathematics, statistics, engineering, or a related field. Strong programming skills and experience in machine learning or statistical modelling are essential. Experience with healthcare data, algorithmic fairness, or deep learning for biomedical data will be advantageous.

Responsibilities: The successful candidate will contribute to high-impact publications, open-source software development, and training materials.

Terms: This position is full-time and fixed-term for 30 months. It is available from January 2026 and must end by 30 November 2028. Applications for flexible working arrangements are welcomed and will be considered in line with business needs.