Computational Chemist – Machine Learned Force Fields, Material Discovery

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

📋 Description

• Design and execute high-throughput quantum chemistry and molecular dynamics campaigns to generate training data for PFAS chemical space.

• Take ownership of reproducible, automated, restartable, and provenance-tracked data-generation workflows across cloud and high-performance computing (HPC) environments.

• Curate and manage datasets, integrating internally generated first-principles data with pertinent public molecular and materials datasets.

• Choose architectures, train, validate, and implement machine-learned interatomic potentials within the PFAS substitution chemical space.

• Fine-tune universal or foundational potentials, or develop models from the ground up when necessary.

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

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

• Conduct extensive prediction campaigns across candidate libraries.

• Deploy trained models, datasets, and reproducible pipelines utilizing SandboxAQ tooling, accompanied by comprehensive documentation.

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

• Validate predictions against actual process constraints, reporting error margins, hold-out performance, and domain-of-validity limits.

• Raise alerts when models are utilized beyond their validated ranges.

⛳️ 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 simulations.

• Proven expertise 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 using production quantum chemistry and electronic structure software such as VASP, Quantum ESPRESSO, CP2K, ORCA, Psi4, or Gaussian.

• Ability to make judicious decisions regarding the level of theory, basis set, and convergence criteria.

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

• Strong programming abilities in Python.

• Practical experience with PyTorch or JAX, including large-scale training on GPU clusters.

• Experience integrating learned potentials with 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, including force-field selection and parameterization for organic and condensed-phase systems.

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

• Experience in system construction, equilibration, and the selection of ensembles, thermostats, and barostats.

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

• Demonstrated rigor in validation processes, including characterizing model errors and out-of-domain failures.

• Experience in cloud and high-performance computing environments.

• Highly desirable: expertise in fluorine-containing chemistry, fluoropolymers, or PFAS-related molecular systems.

• Highly desirable: experience with free-energy calculations, Green-Kubo, or non-equilibrium molecular dynamics.

• Highly desirable: knowledge of long-range electrostatics, polarization, or implicit solvation treatments within learned potentials.

• Familiarity with generative molecular design frameworks.

🏝️ Benefits

• Equity and performance-based incentives.

• Comprehensive health, dental, and vision insurance.

• 401(k) plan with company matching.

• Generous parental leave policy.

• Flexible hybrid work options.

• Generous paid time off (PTO).

• Exposure to senior scientific and executive leadership.

• Mentorship opportunities.

• Dedicated learning budgets.

• Opportunities for professional development.