We are seeking to appoint a Postdoctoral Researcher to develop novel probabilistic statistical machine learning methods to build causal predictive models available in the one-of-a-kind Novartis-Oxford MS (NO.MS) dataset as part of Oxford–Novartis Collaboration for AI in Medicine. The NO.MS is the largest and the most comprehensive dataset on multiple sclerosis (MS), a collection of data on over 40,000 individuals measured longitudinally, some over a decade.
Under the line management of Dr. Habib Ganjgahi and close collaboration with Professors Chris Holmes and Thomas Nichols, you will apply and develop state of the art causal scalable statistical machine learning prognostic models to identify factors and early change-parameters in clinical and MRI images that, on an individual patient level, contribute to a reliable prediction of time to long-term outcomes using clinical, laboratory and high-dimensional image data that can handle missing data and different data modalities and building individual treatment response models to predict which subjects will respond to treatment and heterogenous treatment effect.
Whilst you will be predominantly based at the Big Data Institute, you will also be expected to spend time at the Department of Statistics and participate in the OxCSML research group in Statistics.
You will provide probabilistic machine learning expertise to the Oxford–Novartis Collaboration for AI in Medicine, contributing to the study design and analysis of data alongside the development and application of new analytical methods independently or in collaboration with others. This post will be a key part of the core Oxford analysis team working in collaboration with imaging specialists and other biostatistics and machine learning researchers to deliver optimal research for the collaboration.
You will be responsible for the development, implementation, and evaluation of advanced causal and probabilistic statistical machine learning methodologies for individual-level outcome prediction and treatment response modelling. You will work with large-scale longitudinal clinical, laboratory, and high-dimensional neuroimaging data from the Oxford–Novartis Multiple Sclerosis (NO.MS) dataset to construct scalable prognostic and predictive models capable of handling missing data and heterogeneous data modalities. The role will involve close collaboration with clinicians, statisticians, and machine learning researchers, contributing to study design, statistical analysis plans, and the dissemination of findings through peer-reviewed publications, conference presentations, and internal scientific reports within the Oxford–Novartis Collaboration for AI in Medicine.
It is essential that you hold a PhD/DPhil (or are close to completion) in Statistics, Biostatistics, Statistical Machine Learning, or a closely related quantitative discipline, with demonstrated expertise in statistical model development and algorithmic methodology, particularly within Bayesian or probabilistic frameworks. You must have strong knowledge of modern computational statistics, generative models, causal inference, and predictive modelling, alongside experience in implementing analytical methods using statistical software such as R or MATLAB and scripting languages including Python. The ability to communicate complex methodological concepts effectively and to work collaboratively within a multidisciplinary research environment is essential.
Applications for this vacancy should be made online and you will need to upload a supporting statement and CV. Your supporting statement must explain how you meet each of the selection criteria for the post using examples of your skills and experience. Please restrict your documentation to your CV and supporting statement only. Any other documents will be requested at a later date.
Only applications received before 12 midday on 16 February 2026 will be considered. Please quote184574on all correspondence.
£39,424 to £47,779 per annum. Research Grade 7. This is inclusive of a pensionable Oxford University Weighting of £1,730 per year.
#J-18808-Ljbffr