Postdoctoral Researcher: Atomistic Modeling + ML for Catalysis

Physics World; Albuquerque (NM); Hybrid; USD 60,000 - 90,000; Full time

Job summary

Sandia National Laboratories in Albuquerque invites applications for a postdoctoral researcher in density functional theory and machine learning to join a multidisciplinary materials science team. You will develop high-throughput DFT workflows and build ML/AI models to predict reaction events, integrating them with molecular dynamics codes like LAMMPS to accelerate simulations.

The role emphasizes collaboration and dissemination of findings at conferences and in journals.

Qualifications

• PhD in Materials Science, Physics, Chemistry, Mechanical Engineering, or closely related field.
• Ability to obtain and maintain a DOE Q-level security clearance.

Responsibilities

• Establish a high-throughput workflow that uses DFT to sample chemical reactions.
• Develop an ML/AI framework that can predict chemical reaction events and integrate that framework with molecular dynamics codes (e.g., LAMMPS).
• Plan, conduct, and analyze atomistic simulations to study catalysis in complex material systems.
• Integrate materials knowledge to formulate research hypotheses, propose and carry out research.
• Work in collaborative team environments on multidisciplinary, technically challenging projects as part of a dynamic research organization.
• Communicate accomplishments in presentations at conferences and publications in peer-reviewed journals and engage with program managers to convey impact and research direction.

Skills

DFT expertise

ML for simulations

Python, C++

Graph neural nets

Catalysis simulations

Education

PhD in Materials Science/Physics/Chemistry/ME

Tools

VASP

Quantum Espresso

Gaussian

DFTB+

Job description

Sandia National Laboratories in Albuquerque invites applications for a postdoctoral researcher in density functional theory and machine learning to join a multidisciplinary materials science team. You will develop high-throughput DFT workflows and build ML/AI models to predict reaction events, integrating them with molecular dynamics codes like LAMMPS to accelerate simulations.

The role emphasizes collaboration and dissemination of findings at conferences and in journals.