SandboxAQ - Machine Learning Scientist
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 depth developing and deploying machine learned force fields — including at least one potential that you trained, validated, and put into the hands of other people who now rely on it, whether inside a company or as a public release. We are interested in what you have built and shipped rather than in years served, and this posting is open across experience levels. • Hands-on experience generating first principles training data at throughput with production quantum chemistry and electronic structure codes (e.g. VASP, Quantum ESPRESSO, CP2K, ORCA, Psi4, or Gaussian), including the judgment to set and defend level of theory, basis set, and convergence criteria. • Demonstrated fluency with descriptor based, modern equivariant, and message-passing potential architectures (e.g. MACE, NequIP, Allegro, TensorNet, DeePMD, ANI-class, or FairChem/UMA-family models) — including what each is good for and where each fails. • Strong programming skills in Python and hands on experience with modern ML frameworks (e.g. PyTorch, JAX), including training at scale on GPU clusters. • Practical experience coupling learned potentials into production molecular dynamics engines (e.g. LAMMPS, GROMACS, OpenMM, ASE) and extracting converged physical observables from the resulting trajectories. • Hands-on experience with classical molecular dynamics in those same engines — force field selection and parameterisation for organic and condensed phase systems (e.g. OPLS-AA, AMBER/GAFF, or ReaxFF for reactive chemistry), system construction and equilibration, ensemble and thermostat/barostat choice, and the judgment to say when a classical description stops being trustworthy and a learned potential is required. • Experience building automated computational workflows and curating large scientific datasets — provenance, versioning, and reproducibility. • Demonstrated validation discipline: a track record of characterising model error and out-of-domain failure rather than reporting best case benchmark numbers. • Experience working in cloud and high performance computing environments. • Hands-on experience with fluorine containing chemistry, fluoropolymers, or PFAS-adjacent molecular systems. • Experience computing free energies by thermodynamic cycle or alchemical methods, and/or transport properties by 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
Responsibilities
• Own the training data. Design and run high-throughput physics based simulation campaigns that produce labelled training data for the PFAS chemical space, making the calls that determine whether the data is fit to train on — level of theory, basis set, convergence criteria, sampling strategy, and error budget. • Own the training data. • Build the data generation infrastructure. Stand up automated, restartable, provenance tracked workflows across cloud and HPC by collaborating with the engineering team; curate and version the resulting datasets, and combine internally generated first-principles data with relevant public molecular and materials datasets under consistent conventions. • Build the data generation infrastructure. • Train and own the MLFF stack for the PFAS vertical. Select architectures, train, validate, and deploy machine learned interatomic potentials across the chemical space of PFAS substitution demands. Fine tuning universal or foundation potentials, or training from scratch when appropriate. • Train and own the MLFF stack for the PFAS vertical • Deliver the property predictions the screening pipeline runs on. Build and validate MLFF-driven protocols for the properties our pipelines need — for example protonation and deprotonation energetics underpinning pKa, ion diffusivity in glassy polymer matrices, and Green-Kubo viscosity and thermal conductivity — each benchmarked against reference data or experiment. • Deliver the property predictions the screening pipeline runs on. • Push the potentials into the process chemistries that matter. Extend coverage to resin phase polymerisation and plasma surface etch chemistry, moving beyond single molecule, gas phase behaviour into the condensed phase regime our applications actually occupy. • Push the potentials into the process chemistries that matter. • Run production campaigns and deploy models on our platform. Execute at scale prediction campaigns across full candidate libraries, and land trained models, datasets, and reproducible training pipelines in SandboxAQ tooling so that other scientists can run them from written documentation. • Run production campaigns and deploy models on our platform • Collaborate across the discovery loop, and set the honesty bar. Partner with the generative modeling, molecular property ML, and simulation teams so that MLFF-derived properties are usable as screening oracles and reward signals. Work with our partner facing materials scientists so predictions are checked against real process constraints. Report error bars, hold-out performance, and domain-of-validity limits alongside every predicted property, and escalate when a model is being asked a question it cannot answer. • Collaborate across the discovery loop, and set the honesty bar
Benefits
• US Tier 1$168K – $252K • US Tier 2$151.2K – $226.8K • US Tier 3$134.4K – $201.6K • At SandboxAQ, we are committed to competitive, equitable, and transparent compensation; we continuously benchmark our salaries and total compensation to premium markets to ensure our competitiveness. Individual pay within the above range is determined by job-related skills, experience, education, and geographic location. • With a focus on pay equity and ensuring opportunity for future salary progression, our typical practice is to hire within the first half of the base salary range for a given role and level. This approach allows us to reward performance and increasing expertise consistently as your career develops with us. • We use geographic pay tiers to reflect the pay differences in local markets:For the US: • For the US: • Tier 1: Applies to candidates within 50 miles of New York, San Francisco, San Jose, Seattle, Wash D.C., Boston • Tier 1: • Tier 2: Applies to candidates within 50 miles of Portland, Boulder, Austin, Denver, Chicago, San Diego, Miami, Houston, Dallas, Philadelphia, LA • Tier 2: • Tier 3: Everywhere else in the US • Tier 3: • For the UK: • Tier 1: Applies to candidates within 50 miles of London, Cambridge, Oxford • Tier 1: • Tier 2: Everywhere else in the UK • Tier 2: • For Canada: • Tier 1: Applies to candidates within 50 miles of Toronto & Vancouver • Tier 1: • Tier 2: Everywhere else in Canada • Tier 2: • SandboxAQ is a high-growth company delivering AI solutions that address some of the world's greatest challenges. The company’s Large Quantitative Models (LQMs) power advances in life sciences, financial services, navigation, cybersecurity, and other sectors. • We are a global team that is tech-focused and includes experts in AI, chemistry, cybersecurity, physics, mathematics, medicine, engineering, and other specialties. The company emerged from Alphabet Inc. as an independent, growth capital-backed company in 2022, funded by leading investors and supported by a braintrust of industry leaders. • At SandboxAQ, we’ve cultivated an environment that encourages creativity, collaboration, and impact. By investing deeply in our people, we’re building a thriving, global workforce poised to tackle the world's epic challenges. Join us to advance your career in pursuit of an inspiring mission, in a community of like-minded people who value entrepreneurialism, ownership, and transformative impact. • We offer competitive compensation, a comprehensive benefits package, and opportunities for professional growth. • Compensation: Competitive base salary commensurate with experience, plus equity and performance-based incentives. • Benefits: Comprehensive health, dental, and vision insurance; 401(k) with company match; generous parental leave. • Work-Life Balance: Flexible hybrid work arrangements, generous PTO, and a culture that respects focus time and recovery. • Work-Life Balance: • Career Development: Direct exposure to CHIPS Act-funded programs, senior scientific and executive leadership, mentorship, and dedicated learning budgets to support continued growth. • Career Development: • SandboxAQ Welcomes All • We are committed to fostering a culture of belonging and respect, where diverse perspectives are actively sought and valued. Our multidisciplinary environment provides ample opportunity for continuous growth - working alongside humble, empowered, and ambitious colleagues ready to tackle epic challenges. • Equal Employment Opportunity: All qualified applicants will receive consideration regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, or Veteran status. • Equal Employment Opportunity • Accommodations: We provide reasonable accommodations for individuals with disabilities in job application procedures for open roles. If you need such an accommodation, please let a member of our Recruiting team know. • Accommodations • Read: Guidance for candidates on using AI Tools in interviews • Read: • Guidance for candidates on using AI Tools in interviews
Apply in one click
Upload My Resume
Drop here or click to browse · Tap to choose · PDF, DOCX, DOC, RTF, TXT