Machine Learning Scientist (AI)

Location: Remote within the United States; geographic pay tiers apply based on US location.

Salary: US Tier 1 $168,000–$252,000; US Tier 2 $151,200–$226,800; US Tier 3 $134,400–$201,600 per year, plus equity and performance-based incentives.

Company

SandboxAQ develops AI solutions powered by Large Quantitative Models for life sciences, financial services, navigation, cybersecurity, and other sectors.

What you will do

• Design and run high-throughput quantum chemistry and molecular dynamics campaigns to generate PFAS training data, defining the level of theory, basis sets, convergence criteria, sampling strategy, and error budget.
• Build automated, restartable, provenance-tracked workflows across cloud and HPC; curate, version, and standardize internal and public molecular and materials datasets.
• Train, validate, deploy, and maintain machine learned interatomic potentials for PFAS substitution, including fine-tuning universal or foundation potentials and training models from scratch where appropriate.
• Develop and validate MLFF-driven protocols for pKa-related energetics, ion diffusivity, viscosity, thermal conductivity, and other screening properties against reference data or experiments.
• Extend learned potentials to resin-phase polymerization, plasma surface etch chemistry, and other condensed-phase process chemistries; execute production campaigns across candidate libraries.
• Collaborate with generative modeling, molecular property ML, simulation, engineering, and materials science teams; report error bars, hold-out performance, and domain-of-validity limits for every prediction.

Requirements

• 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 experience developing and deploying machine learned force fields, including at least one potential trained, validated, and delivered for use by others. The role is open across experience levels.
• Hands-on experience generating first-principles training data with production quantum chemistry and electronic structure codes such as VASP, Quantum ESPRESSO, CP2K, ORCA, Psi4, or Gaussian, including selecting and defending theory levels, basis sets, and convergence criteria.
• Fluency with descriptor-based, equivariant, and message-passing potential architectures such as MACE, NequIP, Allegro, TensorNet, DeePMD, ANI-class, or FairChem/UMA-family models, including their strengths and limitations.
• Strong Python programming skills and hands-on experience with modern ML frameworks such as PyTorch or JAX, including training at scale on GPU clusters.
• Practical experience coupling learned potentials into production molecular dynamics engines such as LAMMPS, GROMACS, OpenMM, or ASE, and extracting converged physical observables from trajectories.
• Hands-on experience with classical molecular dynamics, including force-field selection and parameterization for organic and condensed-phase systems, system construction and equilibration, ensemble and thermostat/barostat selection, and assessing when classical models are insufficient.
• Experience building automated computational workflows and curating large scientific datasets with provenance, versioning, and reproducibility.
• Demonstrated validation discipline, including characterizing model error and out-of-domain failure rather than reporting only best-case benchmark results; experience with cloud and high-performance computing environments.

Nice to have

• Hands-on experience with fluorine-containing chemistry, fluoropolymers, or PFAS-adjacent molecular systems.
• Experience computing free energies using thermodynamic-cycle or alchemical methods, and/or transport properties using Green–Kubo or non-equilibrium molecular dynamics.
• Experience with long-range electrostatics, polarization, or implicit-solvation treatments in learned potentials.
• Familiarity with generative molecular design frameworks.

Culture & Benefits

• Remote work within the United States, with flexible hybrid work arrangements also supported by the company.
• Health, dental, and vision insurance; 401(k) with company match; generous parental leave; and generous paid time off.
• Direct exposure to CHIPS Act-funded programs and senior scientific and executive leadership.
• Mentorship, dedicated learning budgets, and a multidisciplinary environment spanning AI, chemistry, cybersecurity, physics, mathematics, medicine, and engineering.
• A culture emphasizing creativity, collaboration, ownership, entrepreneurialism, belonging, and respect for focus time and recovery.