Research Fellow (Chemistry)

Interested applicants are invited to apply directly at the NUS Career Portal. Please note your application will only be processed if you apply via NUS Career Portal.

NUS Career Portal link: https://careers.nus.edu.sg/job/Research-Fellow-%28Chemistry%29/32329-en_GB/st=BB2FF7C3601EEA6D5894A9E83E3953DC8021F728

We regret that only shortlisted candidates will be notified.

Job Description

The successful candidate will join Asst. Prof. LI Xiaoyan's group to advance research in AI-accelerated multiscale simulation and modeling for CCUS.

The main responsibilities of the position include:

. Integrate the density functional theory, molecular dynamics, and continuum modeling to develop a multiscale model
. Utilize the AI/ML method in the multiscale model with higher accuracy and efficiency
. Publish research findings in high-impact journals and present at leading international conferences.
. Contribute to proposal writing and assist in preparing funding applications in support of group research activities.

Qualifications / Discipline:
. PhD in Chemical Engineering, Chemistry, Materials Science, Physics, Computational Science, or a related discipline.
. Proven research track record, evidenced by publications in peer-reviewed journals.
. Excellent communication skills and strong interest in interdisciplinary collaboration.

Skills:
. Expertise in computational materials science, including COMSOL, molecular simulations, density functional theory (DFT), or other continuum models.
. Strong programming skills (Python, C/C++, MATLAB) with experience in ML frameworks such as PyTorch, TensorFlow, and Scikit-learn.
. Skilled in scientific writing and communication, with experience preparing manuscripts for high-impact journals and delivering research presentations at international conferences.

Experience:
. Developed multiscale computational framework
. Strong experience in machine learning and AI-driven modeling for scientific applications, such as machine-learned interatomic potentials and enhanced sampling approaches.
. Collaborated across computational and experimental teams to validate predictions and deepen understanding of structure-property relationships.