Research Fellow (AI for atmospheric transport)

National University of Singapore; Singapore; On-site; SGD 90,000 - 150,000; Full time

Job summary

The National University of Singapore is seeking a Research Fellow in AI for atmospheric transport, based at Kent Ridge Campus. The role involves developing deep-learning frameworks and foundation models to study transport phenomena across a wide range of spatial and temporal scales.

The candidate will work with Python and PyTorch, handle multimodal data, and contribute to high-profile research publications in top AI conferences/journals as part of the Mechanical Engineering unit within the

Qualifications

• PhD in CS/AI/vision or related field.
• Significant research in deep learning for spatiotemporal predictive learning, generative models.
• Experience processing and fusing multimodal data.

Responsibilities

• Develop deep-learning frameworks and foundation models for transport phenomena across spatial and temporal scales.

Skills

Deep learning on spatiotemporal data

Python

PyTorch

Publications in AI conferences

Education

Ph.D. in computer science / AI / computer vision or related field

Tools

Multi-GPU training

High-performance computing platforms

Job description

Job Title: Research Fellow (AI for atmospheric transport)

University-Level Unit: College of Design and Engineering

Faculty/Department-Level Unit: Mechanical Engineering

Employee Category: Research Staff

Location_ONB: Kent Ridge Campus

Posting Start Date: 28/10/2026

Job Description

The candidate will develop deep-learning frameworks and foundation models for transport phenomena across a wide range of spatial and temporal scales.

Qualifications

• A Ph.D. degree in computer science, artificial intelligence, computer vision, or a closely related field.
• Substantial research experience in deep learning on spatiotemporal predictive learning, particularly in generative model.
• Experience in processing and fusing multimodal data.
• Strong programming skills in Python and PyTorch, with experience in large-scale multi-GPU training on high-performance computing platforms.
• A strong publication record, including first-author publications in top-tier AI conferences or leading peer-reviewed journals.