Research Fellow (AI for Materials Discovery)

NANYANG TECHNOLOGICAL UNIVERSITY; Singapore; On-site; SGD 60,000 - 90,000; Full time

Job summary

NTU Singapore’s School of Materials Science and Engineering seeks a Research Fellow to advance AI-driven and data-driven discovery of functional materials. You will develop ML models, perform high-throughput DFT/MD simulations, and build datasets to accelerate energy storage, energy conversion, and electronic materials research.

Collaborating with experimental groups, you will interpret results, guide materials selection, and contribute to manuscript preparation and funding reports.

Qualifications

• PhD in a related discipline.
• Demonstrated research experience in computational materials science, materials informatics, machine learning for materials, or AI-driven materials discovery.
• Strong background in first-principles calculations (DFT), molecular dynamics, and/or high-throughput computational screening.
• Experience in ML/DL areas such as graph neural networks, generative models, transfer or active learning.
• Proficiency in scientific programming and materials simulation software.
• Strong publication record in reputable journals and ability to drive research tasks to completion.
• Excellent written and oral communication for collaboration across disciplines.

Responsibilities

• Develop and apply machine learning and deep learning models for materials property prediction, interpretation, and inverse design.
• Perform high-throughput DFT and MD simulations to understand mechanisms and screen candidate materials for energy and electronic applications.
• Build and curate materials datasets, workflows, and platforms for automated, high-throughput discovery.
• Collaborate with experimental groups to provide mechanistic insights and accelerate exploration.
• Investigate structure–property relationships in electrolytes, cathodes, semiconductors, and related materials.
• Develop interpretable, physics-informed AI approaches to extract insights from data.
• Assist in manuscript preparation, conference presentations, grant development, and reporting to funders.
• Mentor junior researchers and support lab management as needed.

Skills

Machine learning

Graph neural networks

Generative models

Transfer learning

Active learning

Materials informatics

Molecular dynamics

DFT

Programming

Education

PhD in Materials Science

Tools

DFT software

Molecular dynamics

High-throughput screening

Job description

The School of Materials Science and Engineering (MSE) provides a vibrant and nurturing environment for staff and students to carry out inter-disciplinary research in key areas such as Computational Materials Science, Characterisation Materials Science, Defence Composite Materials, Functional Composite Materials, Energy, Nanomaterials, Low Dimensional Materials, Biomaterials Materials, Biological Materials, Bioinspired Materials and Sustainable Materials.

For more details, please view https://www.ntu.edu.sg/mse/research.

We are seeking a highly motivated and interdisciplinary Research Fellow to support the development of AI-driven and data-driven approaches for the discovery and design of functional materials. The role will involve the development and application of machine learning models, high-throughput first-principles (DFT/MD) simulations, and generative AI to predict, interpret, and design materials for energy storage, energy conversion, and electronic applications. The successful candidate will contribute to NTU’s research in advanced materials by bridging computational materials science, artificial intelligence, and close collaboration with experimental efforts.

Key Responsibilities:

• Develop and apply machine learning and deep learning models (e.g., graph neural networks, generative models, transfer learning) for materials property prediction, interpretation, and inverse design.
• Perform high-throughput first-principles (DFT) and molecular dynamics (MD) simulations to understand mechanisms and screen candidate materials for energy and electronic applications.
• Build and curate materials datasets, workflows, and platforms to enable automated and high-throughput materials discovery.
• Collaborate closely with experimental groups to provide mechanistic insights, guide materials selection, and accelerate hypothesis-driven exploration.
• Investigate structure-property relationships in electrolytes, cathodes, semiconductors, and related functional materials for energy storage, conversion, and electronic applications.
• Develop interpretable and physics-informed AI approaches to extract chemical and physical insights from computational and experimental data.
• Assist in manuscript preparation, conference presentations, grant development, and reporting to funding agencies and collaborators.
• Mentor junior researchers and students, and support general laboratory management, procurement and equipment coordination where required.

Job Requirements:

• PhD in Materials Science, Computational Chemistry/Physics, Chemical/Electronic Engineering, Computer Science, or a related discipline.
• Demonstrated research experience in computational materials science, materials informatics, machine learning for materials, or AI-driven materials discovery.
• Strong background in first-principles calculations (DFT), molecular dynamics, and/or high-throughput computational screening.
• Experience in one or more of the following areas is highly desirable: machine/deep learning (graph neural networks, generative models, transfer or active learning), materials informatics, energy storage and conversion materials, electronic materials, or interpretable and physics-informed machine learning.
• Proficiency in scientific programming and materials simulation software.
• Strong publication record in reputable journals and the ability to independently drive research tasks to completion.
• Good written and oral communication skills, with the ability to work effectively in a multidisciplinary and collaborative research environment.

We regret to inform that only shortlisted candidates will be notified.