Research Fellow (Cardiac Modelling and Simulation)

Interested applicants are invited to apply directly at the

Your application will be processed only if you apply via

We regret that only shortlisted candidates will be notified.

Job Description

We aim to develop advanced AI-driven models for constructing cardiac digital twins-personalized virtual heart models that integrate multi-modal patient data, including medical imaging, electrocardiograms (ECG), and electronic health records. Our research focuses on high-fidelity cardiac simulations, including electrophysiological (EP) modelling to study arrhythmias and electrical conduction abnormalities, as well as biomechanical simulations to analyse cardiac deformation and hemodynamic. By combining AI techniques with computational cardiac modelling, we seek to uncover mechanistic insights into heart diseases, enabling more precise diagnosis, risk stratification, and personalized treatment strategies. This research sits at the intersection of AI and cardiac sciences, pushing the boundaries of digital twin technology to revolutionize patient-specific simulations. We will collaborate with a multi-disciplinary team of experts from NUS, University of Oxford, Imperial College London, and Fudan University, fostering a cutting-edge research environment that bridges AI, medical imaging, and computational cardiology.

The selected candidate is supposed to perform the followings:

• Develop and validate novel multi-modal AI frameworks for integrated cardiac analysis, fusing imaging, electrophysiological, biomechanical, and clinical data.
• Design, implement, and benchmark deep learning models for cardiac mesh reconstruction, segmentation, and functional simulation (e.g., from cine MRI, CT, or echocardiography).
• Advance physics-informed or hybrid AI models for cardiac biomechanics and electrophysiology simulation.
• Collaborate with clinicians and data scientists to translate AI-driven tools into actionable clinical insights and workflows.
• Publish research in top-tier journals and conferences and contribute to open-source software in cardiac digital health.

Qualifications

• Possess a PhD degree in biomedical engineering, computer science, computational physics, applied mathematics, or a related field.
• Strong self-motivation and enthusiasm for AI applications in healthcare, particularly in cardiac digital twins.
• Extensive experience in cardiac simulation and modelling, such as electrophysiological (EP) simulations, cardiac mechanics, or multi-scale heart modelling.
• Strong problem-solving skills and a proven research track record, demonstrated by first-author publications in top-tier journals and conferences.
• Proficiency in programming (Python, C++, MATLAB) and familiarity with computational frameworks for cardiac modelling (e.g., FEM-based solvers, PINNs, or cardiac electrophysiology software).
• Strong written and spoken communication skills, including scientific writing and presentations.
• Open to fixed-term contract.