Postdoctoral Research Associate in Biostatistics (R Package Developer)

Job id: 098666. Salary: £44,105 – £47,632 per annum inclusive of London Weighting Allowance.

Posted: 01 November 2024. Closing date: 02 December 2024.

Business unit: IoPPN. Department: Biostatistics & Health Informatics.

Location: Denmark Hill Campus. Category: Research.

About Us

The Department of Biostatistics and Health Informatics is a major force in developing quantitative methodology as applied to mental health research. The department’s research spans a range of approaches, including prediction modelling, clinical trials, causal inference, and the application of large language models to unstructured medical records.

This role will sit within the Precision Medicine and Statistical Learning Group, which uses statistical and machine learning methods to develop models that enable healthcare providers to make informed decisions about patient care.

About The Role

We seek a motivated postdoctoral researcher with strong R programming skills to join a research team developing an innovative open-source R package to calculate sample sizes for prediction modelling. The package will use simulation to estimate minimum sample sizes for machine learning and longitudinal models, providing a vital tool for researchers and clinicians.

The successful candidate will play a central role in all stages of package development, including the technical development of the software, engaging with users, creating comprehensive package documentation, and writing scientific publications.

This is an exciting opportunity for a candidate interested in applied statistical programming, machine learning, and software development, particularly within healthcare research. They will join an established team at the forefront of clinical prediction modelling and will be supported by statisticians and methodologists with extensive expertise in clinical prediction modelling and software development.

The main responsibilities will include developing new features to incorporate machine learning algorithms, such as random forests and gradient-boosted trees, as well as longitudinal models like joint models and landmarking. The individual will also implement surrogate modelling approaches, including Gaussian process models, and validate the software’s functionality through benchmarking studies.

An important part of the role will be writing and maintaining comprehensive documentation for the R package to ensure accessibility for users from both research and clinical backgrounds. The individual will lead the writing of research papers for publication, present findings at international conferences, and collaborate closely with patients and researchers, incorporating their feedback to create user-friendly software interfaces.

This is a full-time (35 hours per week) fixed-term contract for 16 months.

The successful candidate will jointly report to Dr Ewan Carr and Mr Gordon Forbes. For any questions about the role or to discuss informally, please contact ewan.carr@kcl.ac.uk or gordon.forbes@kcl.ac.uk.

About You

To be successful in this role, we are looking for candidates who have the following skills and experience:

Essential criteria

• A PhD in a relevant discipline (e.g., statistics, computer science, mathematics, psychology or a related field) or equivalent experience.
• Strong proficiency in R programming.
• Experience in either longitudinal modelling, machine learning, or simulation studies.
• Familiarity with statistical modelling and simulation techniques, particularly in healthcare or prediction modelling contexts.
• Ability to work independently as well as within a multidisciplinary team.

Desirable criteria

• Experience with software version control tools (e.g., GitHub) and collaborative coding practices.
• Experience with high-performance computing environments for running large-scale simulations.
• Demonstrated experience in writing, maintaining, and developing R packages or other open-source software.
• Experience communicating with diverse stakeholders, including public and patient involvement (PPI) or user engagement activities, through various mediums such as blog posts, videos, or other accessible formats.
• Experience in writing and contributing to scientific publications.