Machine Learning Scientist - Molecular Force Fields

What you'll do

• Design and run high-throughput quantum chemistry and molecular dynamics campaigns; build reproducible data-generation workflows.
• Train, validate, and deploy machine-learned potentials and property-prediction protocols across PFAS-substitution chemistry.
• Run production prediction campaigns, document model limitations, and collaborate with scientific and materials teams to validate candidates.

What they ask for

• PhD in Computational Chemistry, Materials Science, Physics, Machine Learning, or a related field, with deep specialization in machine-learned interatomic potentials or atomistic simulation.
• Demonstrated development and deployment of machine-learned force fields, including a trained and validated potential used by others.
• Experience generating first-principles training data with production quantum chemistry or electronic-structure codes.
• Strong Python and modern ML-framework skills, plus experience with GPU clusters, molecular dynamics engines, automated workflows, and cloud or HPC environments.

Nice to have

• Experience with fluorine-containing chemistry, fluoropolymers, or PFAS-adjacent systems.
• Experience with free-energy or transport-property calculations, long-range electrostatics, polarization, implicit solvation, or generative molecular design.

Pay

$134.4K – $252K (base salary; multiple ranges)

Tools

VASP, Quantum ESPRESSO, CP2K, ORCA, Psi4, Gaussian, Python, PyTorch

AI focus

Train and apply machine-learned interatomic potentials for molecular simulation and PFAS-substitute discovery.