AI4X Postdoctoral Fellow

The AI4X Postdoctoral Fellowship supports outstanding early-career researchers who leverage Artificial Intelligence (AI) to accelerate breakthroughs across science, technology, engineering, and mathematics, including medicine (STEM). Through the AI4X-PDF, we seek to nurture the next generation of research leaders working at the intersection of AI and STEM, driving innovation and strengthening Singapore's AI-for-Science ecosystem.

The candidate is expected to conduct the following research works

• Perform first-principles calculations on bulk systems, surfaces, and nanostructures as required.

• Develop AI/ML models for predicting materials properties using data-driven approaches, including the treatment of disordered inorganic materials.

• Develop codes as necessary to assist existing and new code frameworks for advanced property prediction and analysis of inorganic disordered materials.

• Carry out machine-learning based first-principle calculations aimed at advancing the understanding defect-based generative design

• Analyze, interpret, and present research results in group meetings, workshops, and international conferences.

• Disseminate research outcomes through high-impact journal publications, conference presentations, and data releases in accordance with open science and FAIR data principles.

• Collaborate closely with experimental researchers and external partners, including collaborators in academia, industry, and national laboratories

Job Requirements:

• PhD in Materials Science, Chemistry, Physics, Computer Science, or a closely related discipline.

• Strong experience with Density Functional Theory (DFT) calculations using established codes (e.g., VASP, FHI-aims).

• Demonstrated experience with traditional methods for modeling atomic site disorder, such as special quasi-random structures (SQS), partial occupancies, and cluster expansion techniques.

• Hands-on experience with materials simulation tools and libraries (e.g., ASE, pymatgen, LAMMPS) and high-throughput computational frameworks (e.g., atomate2, AFLOW).

• Extensive knowledge of graph-based machine learning models for interatomic potentials, along with experience in generative models for the inverse design of inorganic materials.

• Proficiency in at least one programming language for data science and numerical computing (e.g., Python, Fortran).

We regret that only shortlisted candidates will be notified.