MARS Senior Research Associate in Machine Learning for Infectious Disease Models

MARS: Mathematics for AI in Real-world Systems is seeking a highly motivated and creative Senior Research Associate to join our interdisciplinary team at the frontier of computational epidemiology and machine learning. This role focuses on developing next-generation frameworks to predict, understand, and mitigate the spread of infectious diseases.

The successful candidate will lead research in one (or both) of the following cutting-edge areas:

Generative Inference and Monte Carlo Optimisation:

• Developing new generative machine learning approaches, to improve the efficiency of high-dimensional Monte Carlo algorithms for stochastic epidemic models. Research directions may include discrete normalising flows, diffusion-based methods, online reinforcement learning methods, amortized inference. The aim is to solve one of the last remaining barriers to successful disease modelling at scale, delivering faster and more reliable inference, better-calibrated predictive uncertainty, and computational tools for large-scale mechanistic models.

Probabilistic Modelling of Higher-Order Contact Structure:

• Developing novel machine learning and statistical methodology for latent relational structure in populations, including higher-order, group-based, and temporally evolving interactions. Directions may include probabilistic graph and hypergraph models, generative approaches to large-scale contact networks, learning from partial or aggregate observations, and principled uncertainty quantification. The goal is to build scalable methods for inference and intervention-aware analysis in complex epidemic systems, with applications to targeted intervention design in settings such as schools, workplaces, and hospitality.

Key responsibilities:

• Develop and implement novel ML architectures and computationally intensive statistical methodology tailored to outbreak datasets.
• Collaborate with public health stakeholders and data providers to ensure models are grounded in real-world contact patterns.
• Publish findings in high-impact journals (e.g., Nature Communications, Lancet Digital Health) and top-tier ML conferences (NeurIPS, ICML, ICLR).
• Contribute to an open-source codebase to ensure reproducibility and utility for the wider scientific community.

The successful applicant will work within a vibrant community of infectious disease modellers, centred in MARS, but collaborating with colleagues in Lancaster Medical School. There is additional scope to work within a wider collaboration with the University of St Andrews and Liverpool School of Tropical Medicine in Global Health, human, animal, and OneHealth epidemiology, as well as engage in consultancy, teaching, and outreach activities relevant to the research.

This is a full-time, fixed term position until 31st July 2029. Flexible working arrangements will be considered but you will be expected to be present on the Lancaster campus a minimum of two days a week.

Closing date: 17th May 2026

For further information and details of how to apply, please visit: https://hr-jobs.lancs.ac.uk/Vacancy.aspx?ref=0308-26

Lancaster University promotes equality of opportunity and diversity within the workplace. For these positions, we welcome applications from all diversity groups but particularly from women who are currently underrepresented in the mathematical sciences.

Photo by Daniel Dan