Computational Chemist - Machine Learned Force Fields, Material Discovery

About this role

Develop and deploy machine-learned force fields to accelerate the discovery of PFAS-lean or PFAS-free substitutes for semiconductor materials. The role spans first-principles data generation, model training and validation, and production-scale property prediction, with results checked against experiments and real process constraints.

About the company

SandboxAQ leverages artificial intelligence and quantum technology to improve decision-making processes across various sectors, including life sciences and medical devices. The company focuses on developing innovative solutions that address complex challenges in data analysis, research, and product management.

The team

PFAS team within the Chemical Simulation (ChemSim) group.

Stack

What you'll do

• Design and run high-throughput quantum chemistry and molecular dynamics campaigns to generate training data.
• Build automated, restartable, provenance-tracked workflows across cloud and HPC; curate and version datasets.
• Train, validate, and deploy machine-learned interatomic potentials, including fine-tuning existing models or training from scratch.
• Develop and benchmark MLFF-based protocols for properties such as pKa, diffusivity, viscosity, and thermal conductivity.
• Extend potentials to polymerization and plasma surface-etch chemistry in condensed-phase systems.
• Run large-scale prediction campaigns and make models, datasets, and reproducible pipelines available to other scientists.
• Report uncertainty, hold-out performance, and model domain limits; collaborate across modeling and experimental validation teams.

What we're looking for

• PhD in computational chemistry, materials science, physics, machine learning, or a related field, with deep expertise in atomistic simulation or learned potentials.
• Have trained, validated, and deployed at least one machine-learned force field used by others.
• Experience generating first-principles training data with electronic-structure codes and selecting defensible theory, basis sets, and convergence criteria.
• Fluency with descriptor-based, equivariant, and message-passing potential architectures and their limitations.
• Strong Python and PyTorch or JAX skills, including GPU-cluster training.
• Experience integrating learned potentials with production MD engines and extracting converged physical observables.
• Hands-on classical MD experience, including force-field selection, system setup, equilibration, and ensemble choices.
• Experience building reproducible computational workflows and scientific datasets, validating model errors and out-of-domain behavior, and working in cloud/HPC environments.

Nice to have

• Experience with fluorinated chemistry, fluoropolymers, or PFAS-adjacent systems.
• Free-energy calculations using thermodynamic cycles or alchemical methods, or transport-property calculations using Green-Kubo or non-equilibrium MD.
• Experience with long-range electrostatics, polarization, or implicit-solvation treatments in learned potentials.
• Familiarity with generative molecular design frameworks.

Benefits

• Equity and performance-based incentives.
• Health, dental, and vision insurance.
• 401(k) with company match.
• Generous parental leave and PTO.
• Flexible hybrid work arrangements.
• Dedicated learning budgets.