Machine Learning Scientist – Molecular Force Fields

This is a fully remote position, open to applicants in United States.

📋 Description

• Create and execute high-throughput quantum chemistry and molecular dynamics initiatives to generate training data for PFAS chemical domains.

• Maintain reproducible infrastructure for the generation of physics-based simulation data.

• Establish the level of theory, basis set, convergence criteria, sampling strategy, and error budget.

• Develop automated, restartable, and provenance-tracked workflows across cloud and HPC environments.

• Organize and version both internally produced and publicly available molecular and materials datasets.

• Choose architectures, train, validate, and deploy machine-learned interatomic potentials for PFAS substitution.

• Refine universal or foundational potentials, or create models from the ground up when necessary.

• Construct and validate MLFF-driven protocols for protonation/deprotonation energetics, ion diffusivity, viscosity, and thermal conductivity.

• Expand potentials to resin-phase polymerization and plasma surface etching chemistry.

• Conduct production prediction campaigns across candidate libraries.

• Implement trained models, datasets, and reproducible training pipelines using SandboxAQ tools.

• Collaborate with teams involved in generative modeling, molecular property machine learning, simulation, and materials science.

• Provide error bars, hold-out performance metrics, and domain-of-validity limits for predicted properties.

• Raise concerns when models are queried beyond their capabilities.

⛳️ Requirements

• PhD in Computational Chemistry, Materials Science, Physics, Machine Learning, or a related discipline, with a strong focus on machine-learned interatomic potentials or atomistic simulation.

• Proven experience in developing and deploying machine-learned force fields, including at least one potential that has been trained, validated, and utilized by others.

• Practical experience in generating first principles training data at scale using production quantum chemistry and electronic structure software such as VASP, Quantum ESPRESSO, CP2K, ORCA, Psi4, or Gaussian.

• Ability to establish and defend the level of theory, basis set, and convergence criteria.

• Proficiency with descriptor-based, modern equivariant, and message-passing potential architectures like MACE, NequIP, Allegro, TensorNet, DeePMD, ANI-class, or FairChem/UMA-family models.

• Strong programming capabilities in Python.

• Practical experience with contemporary ML frameworks such as PyTorch and JAX.

• Experience in large-scale training on GPU clusters.

• Hands-on experience integrating learned potentials into production molecular dynamics engines such as LAMMPS, GROMACS, OpenMM, or ASE.

• Experience in extracting converged physical observables from molecular dynamics trajectories.

• Hands-on experience with classical molecular dynamics, force field selection, and parameterization for organic and condensed phase systems.

• Familiarity with OPLS-AA, AMBER/GAFF, or ReaxFF for reactive chemistry.

• Experience in system construction and equilibration, as well as ensemble and thermostat/barostat selection.

• Experience in building automated computational workflows and managing large scientific datasets with provenance, versioning, and reproducibility.

• Demonstrated validation discipline, including assessment of model error and out-of-domain failures.

• Experience working in cloud and high-performance computing settings.

• Candidates are ineligible to participate in foreign talent programs sponsored by China, Russia, Iran, or North Korea due to federal grant stipulations.

🏝️ Benefits

• Competitive base salary aligned with experience.

• Equity options.

• Incentives based on performance.

• Comprehensive health, dental, and vision coverage.

• 401(k) plan with company matching.

• Generous parental leave policy.

• Flexible hybrid work arrangements available.

• Generous paid time off.

• Direct involvement in CHIPS Act-funded initiatives.

• Mentorship opportunities.

• Dedicated learning budgets.

• Reasonable accommodations for individuals with disabilities during the job application process.