University of Cambridge

Job Opportunities


Research Associate (Fixed Term)

An opportunity has arisen for a talented statistician or probabilistic machine learning researcher at the MRC Biostatistics Unit, Cambridge University, within the Precision Medicine and Inference for Complex Outcomes theme.

The successful applicant will have the opportunity to contribute to the Bringing Innovative Research Methods to Clustering Analysis of Multimorbidity (BIRM-CAM) project between the Universities of Cambridge and Birmingham, funded by the UK Medical Research Council (MRC) and the National Institute for Health Research (NIHR). The project is led by Profs. Sylvia Richardson (Cambridge) and Tom Marshall (Birmingham). Within the MRC Biostatistics Unit, Drs. Steven Kiddle, Jessica Barrett, and Paul Kirk are co-investigators and part of the BIRM-CAM team.

Multimorbidity is when people suffer from more than one long-term illness. It is increasingly common as people live longer. It is important because: individual illnesses have knock-on effects on others, it is more complex managing multiple than single illnesses, and multimorbid patients are heavy users of medications and health services. Electronic health records (EHRs) are a good source of information on multimorbidity because they include information on the same patient over many years. As part of the BIRM-CAM project, we will be developing and applying sophisticated data analysis techniques to extract relevant information about multimorbidity from EHRs.

We are seeking an ambitious and motivated individual to join the BIRM-CAM research team and enhance its analytics. The project focuses on the development and refinement of clustering and predictive models that use EHRs to identify new multimorbidity groupings and patterns associated with health outcomes such as hospital admission or death, and explore how groups of illnesses develop sequentially in individual patients. Relevant statistical modelling techniques include (supervised and unsupervised) Bayesian clustering techniques, kernel methods, and multi-state time-to-event predictive models.

The successful candidate will have a PhD in a strongly quantitative discipline, ideally statistics or probabilistic machine learning. Past experience with EHRs and/or other "big data" sources would be advantageous, but not essential; training will be given on the basic concepts necessary to the post. A desire to address questions of substantive biomedical and societal importance is essential. Good communication skills and an enthusiasm for collaborating with others (including non-statisticians) are also essential. Strong programming ability would be desirable, and experience of computational statistical methods would be highly advantageous. The successful applicant will be supported in their career development with a range of formal courses and on-the-job training.

For an informal discussion about this post please contact: or

Fixed-term: The funds for this post are available for 30 months in the first instance.

Click the 'Apply' button below to register an account with our recruitment system (if you have not already) and apply online.

Closing date: 12th March 2020

Interview date: 24th March 2020

Please ensure that you upload a covering letter and CV in the Upload section of the online application. The covering letter should outline how you match the criteria for the post and why you are applying for this role. If you upload any additional documents which have not been requested, we will not be able to consider these as part of your application.

Please include details of your referees, including email address and phone number, one of which must be your most recent line manager.

Please quote reference SL22497 on your application and in any correspondence about this vacancy.

The University actively supports equality, diversity and inclusion and encourages applications from all sections of society.

The University has a responsibility to ensure that all employees are eligible to live and work in the UK.

Further information

Apply online