Postdoctoral Fellow - AI-Driven Materials Discovery

University at Buffalo; Buffalo (NY); Hybrid; USD 36,000 - 60,000; Full time

Job summary

The University at Buffalo invites applications for a full-time Postdoctoral Associate in the Peng Research Group to conduct research at the intersection of scientific AI, atomistic simulation, computational catalysis, and data-driven materials discovery.

The successful candidate will work independently and collaboratively, focusing on developing reproducible computational workflows, leveraging Python, Linux, and HPC, and contributing to high-impact projects in materials design.

Qualifications

• Doctoral degree in materials science and engineering, chemical engineering, chemistry, physics, computational science, or a closely related field. All degree requirements, including the dissertation, must be completed by the date of appointment.
• Demonstrated research experience with density functional theory or closely related first-principles atomistic simulation methods.
• Demonstrated research experience applying artificial intelligence or machine learning to scientific or engineering problems, including the development, training, validation, or evaluation of machine-learning models.
• Proficiency in Python and experience working in Linux and high-performance-computing environments.
• Experience developing or using automated and reproducible computational research workflows.
• Ability to conduct computational research independently and analyze and interpret research data.
• Strong written and oral communication skills and the ability to work effectively in a collaborative research environment.

Skills

Python

Linux

HPC environments

Independent research

Communication skills

Education

Doctoral degree (MSE/ChE/Chem/Physics/Computational Science or related)

Job description

The University at Buffalo invites applications for a full-time Postdoctoral Associate in the Peng Research Group to conduct research at the intersection of scientific AI, atomistic simulation, computational catalysis, and data-driven materials discovery.

The successful candidate will work independently and collaboratively, focusing on developing reproducible computational workflows, leveraging Python, Linux, and HPC, and contributing to high-impact projects in materials design.