Job Description

About the Role
The Centre for Epidemic Response & Modelling (CERM) at NUS Saw Swee Hock School of Public Health invites applications for a Research Fellow to drive AI-centred research within a portfolio that spans decision-support for pandemic response, social network modelling, equitable AI for clinical applications, and developing culturally-congruent LLMs to advance behavioural modelling in public health.

The postholder will work with Asst. Prof. Swapnil Mishra (Deputy Director, CERM and AI for Public Health Programme) and engage an active network of collaborators spanning CERM, NUS, Imperial College London, Ashoka University, the Communicable Diseases Agency Singapore (CDA), the National Environment Agency Singapore (NEA), the Machine Learning & Global Health Network (MLGH), and wider regional and global partners. They will have significant latitude to shape their research direction within these themes and will collaborate closely with engineers, epidemiologists, clinicians, and policy stakeholders.

Key Responsibilities
• Develop and validate deep learning and machine learning models for behaviour modelling,
including foundation models, graph neural networks (GNNs), and sequence models applied
to public data for good.
• Prototype and evaluate reinforcement learning frameworks for simulating and optimising
public health interventions under uncertainty.
• Build AI pipelines for social network and information diffusion modelling; explore LLMbased
simulation of intervention scenarios.
• Publish findings in leading venues.
• Co-supervise junior researchers; contribute to grant reporting and proposal writing.

Additional Opportunities
The group actively supports career development through conference travel, training workshops, and mentorship from senior researchers and international collaborators.

Qualifications

• PhD in computer science, machine learning, data science, computational epidemiology, or
a closely related field.
• Strong expertise in deep learning frameworks (PyTorch, JAX, or TensorFlow); experience
with LLMs or foundation models is a significant advantage.
• Proficiency in Python; familiarity with R is beneficial but not required.
• Experience in at least two of: time-series forecasting, GNNs, reinforcement learning,
NLP/LLMs, computer vision, or causal inference.
• Demonstrated publication record commensurate with career stage.
• Interest in real-world public health and policy impact; ability to communicate technical work
to non-specialist audiences.

Interested applicants should submit the following documents:
• A cover letter explaining your interest in the position, relevant experience, and research vision.
• A comprehensive curriculum vitae, including a full list of publications.
• A research statement (maximum two pages) outlining past contributions and future directions.
• Contact information for two professional references (letters may be requested).