Job Description
Research Fellow (Artificial Intelligence & Federated Learning)
The Saw Swee Hock School of Public Health, National University of Singapore (NUS), invites applications for a full-time Research Fellow position to join a multidisciplinary research programme focused on developing advanced AI-driven methods for neuroimaging, digital phenotyping, and population brain health.
This programme brings together expertise in artificial intelligence, neuroimaging, data science, and public health to advance early detection and prevention of cognitive decline and ageing-related brain disorders. The research team works closely with local and international collaborators across clinical, academic, and industry settings to develop privacy-preserving machine learning approaches, federated learning frameworks, and interpretable algorithms for multimodal health data.
The successful candidate will play a central role in designing and implementing AI models, federated learning workflows, and computational pipelines, with opportunities to contribute to high-impact publications, methodological innovation, and translation of research findings into real-world applications.
Key Responsibilities
AI Research & Algorithm Development
• Work closely with the Principal Investigator (PI) to design and implement AI and machine-learning models for neuroimaging, blood biomarkers, and clinical datasets.
• Develop deep learning architectures (e.g., CNNs, transformers, autoencoders) and multimodal data integration models.
• Conduct rigorous data processing, model training, validation, and explainable AI analysis.
• Contribute to the development of harmonisation and bias-assessment pipelines to ensure robust model performance across diverse cohorts.
Federated Learning & Privacy-Preserving Analytics
• Develop and deploy federated learning frameworks across multiple datasets and institutional partners.
• Implement privacy-preserving technologies such as secure aggregation, differential privacy, or encrypted computation.
• Address challenges related to cross-site heterogeneity, data harmonisation, and model generalisability.
• Maintain documentation, computational workflows, and reproducible code repositories.
Project Management & Collaboration
• Work collaboratively with clinicians, data scientists, imaging specialists, and industry partners to support project execution.
• Engage with external partners to coordinate data-sharing, federated learning infrastructure, and research activities.
• Support ethics applications, progress reporting, and grant-related documentation.
Knowledge Generation & Dissemination
• Lead or contribute to scientific manuscripts, conference abstracts, and technical reports.
• Prepare high-quality presentations, visualisations, and summaries for stakeholders, funders, and academic audiences.
• Mentor students or junior researchers involved in AI and imaging sub-projects.
Additional Information
• This is a full-time position based at NUS.
• Recruitment is open immediately, and applications will be reviewed on a rolling basis until the position is filled.
• For further inquiries, please contact Dr. Saima Hilal at saimahilal@nus.edu.sg.
Note: Only shortlisted candidates will be contacted.
Qualifications
Requirements
• PhD in Computer Science, Artificial Intelligence, Machine Learning, Biomedical Engineering, Data Science, or a related field.
• Strong background in AI, deep learning, and/or federated learning, supported by publications.
• Demonstrable proficiency with machine learning frameworks (e.g., PyTorch, TensorFlow).
• Experience with federated learning toolkits such as TensorFlow Federated, Flower (FLwr), NVIDIA FLARE, or PySyft.
• Strong programming skills (Python preferred), with familiarity in GPU or distributed computing environments.
• Experience with biomedical or neuroimaging data is advantageous but not required.
• Excellent analytical, writing, and communication skills.
• Ability to work effectively within an interdisciplinary team and engage diverse stakeholders.
More Information
Location: Kent Ridge Campus
Organization: Saw Swee Hock School of Public Health
Department : Saw Swee Hock School of Public Health
Employee Referral Eligible: No
Job requisition ID : 31031
