Research Fellows (Postdoctoral Scholars)
OpenWe are recruiting full-time Research Fellows to develop hybrid physics-AI for fluid mechanics and fluid-structure interaction, towards weather applications and engineering applications in the maritime sector.
- Location: Singapore
- Type: Full-time
- Deadline: Open until filled
The Team
MathEXLab is an intesrdisciplinary research lab at the National University of Singapore (NUS), led by Assistant Professor Gianmarco Mengaldo. We develop next-generation mathematical modelling and AI methods for understanding and predicting complex systems, with applications in weather and climate, fluid mechanics, robotics, and socio-technical systems. NUS AI Institute was established on 25 March 2024 at the National University of Singapore, under the direction of Professor Mohan Kankanhalli, Provost’s Chair Professor of Computer Science. The institute aims to bring together AI researchers across NUS, spanning foundational and applied AI and its societal impacts — combining core research with deep domain expertise to harness AI for the public good.
What you will do
- Develop and benchmark multimodal AI / foundation-model approaches for spatiotemporal forecasting.
- Build reproducible AI training and evaluation pipelines, as well as uncertainty quantification strategies.
- Work at the intersection of physics and AI, with an emphasis on geospatial computational modelling.
- Collaborate with domain experts and, where relevant, operational stakeholders.
- Drive scientific breakthroughs and contribute to publications and cross-institutional collaborations.
Skills & qualifications required / strongly preferred
- PhD in Computer Science, Data Science, Engineering, Physics, or a related field.
- Strong Python and PyTorch experience; experience with multi-GPU/distributed training and performance optimization.
- Experience with real-world geospatial/sensor data, including quality control, cleaning, and visualization.
- Strong communication and collaboration skills.
- Deep learning expertise in generative models, physics-aware learning, or uncertainty modelling is highly desirable.
- Experience with dense spatiotemporal prediction, for example computational fluid dynamics applied to weather and climate, is highly desirable.
Contract
Initial appointment: 1-year contract, renewable.
Compensation
Competitive salary commensurate with qualifications and experience.
How to apply / contact
- Assistant Professor Gianmarco Mengaldo | Email: mpegim@nus.edu.sg.
- Please include: CV, a short statement of research interests and fit, and 1–3 representative papers or a code repository link.