Interested applicants are invited to apply directly at the NUS Career Portal

Your application will be processed only if you apply via NUS Career Portal

We regret that only shortlisted candidates will be notified.

Job Description

The National University of Singapore (NUS), Department of Computer Science, is seeking a highly motivated and talented Research Assistant to join our team investigating the use of Physics Informed Graph Neural Networks for Hydrology. This project aims to develop and evaluate a new benchmark for Flood prediction, using modern deep learning techniques such as GNNs, while incorporating physics constraints in the model architecture.

Responsibilities

• Conduct research on graph neural network architectures and hydrological constraints governed by physics.
• Integrate the hydrological constraints such as shallow water equations and develop physics informed deep learning model architectures.
• Curate and standardize a dataset for flood modeling.
• Analyze and interpret the propose physics informed model architecture on the new benchmark dataset.
• Technical setup of a Kaggle contest, which will be run for the new benchmark as a global - public contest.
• Consolidate the results from all entries to the contest as a research publication

Qualifications

• Bachelor's degree in Computer Science, Data Science, Artificial Intelligence, or a related field (a Master's degree is an advantage).
• Strong background in machine learning, with prior exposure to Graph Neural Networks or deep learning methods preferred.
• Demonstrated experience in conducting independent research, including problem formulation, experimentation, and analysis.
• Proficiency in Python and relevant machine learning frameworks (e.g., PyTorch, TensorFlow).
• Familiarity with scientific computing, numerical methods, or physics-informed modeling is desirable.
• Excellent problem-solving skills, with the ability to work both independently and collaboratively across disciplines.
• Strong written and verbal communication skills, with experience preparing technical reports or academic papers an asset.

Plans & Goals for Candidate:

• Gain expertise in applying physics-informed GNNs to real-world flood modeling problems.
• Build and release a high-impact, open-access flood modeling dataset.
• Successfully launch and manage a global Kaggle challenge to engage the wider AI community.
• Publish high-quality research papers and reports based on project findings.
• Develop cross-disciplinary skills by working closely with hydrology and climate science experts.