Applied ML Researcher (Molecular Simulation) in Cambridge

CuspAI is the frontier AI company on a mission to solve the breakthrough materials needed to power human progress. While nature took billions of years to perfect molecules, we are harnessing AI to unlock trillion-dollar materials breakthroughs in months, not millennia. Our founding team is the most cited in the world, comprised of world‑class researchers in AI, chemistry and engineering. We are working on some of the hardest and most important challenges including energy, clean water, the future of compute, and carbon capture, and this is just the start of what our ‘search engine’ for next‑generation materials will unlock. We invite you to be part of a diverse, innovative team at the intersection of AI and materials science, working to create impactful partnerships that drive innovation, scalability, and industry collaboration. This work matters. Your work matters.

Due to growth, we are seeking an Applied ML Researcher (Molecular Simulation) to advance our molecular simulation capabilities, developing next–generation computational methods that bridge molecular‑scale physics with continuum–level phenomena. Note that you would be joining as a ‘Member of Technical Staff’, but the indicative job title above hopefully helps to explain the nature of this role. Hiring timelines: We’re aiming to start interviewing for this role in February and would like to make an offer by the end of March.

Simulating how molecules behave under realistic conditions is one of the key bottlenecks in materials discovery. Current tools are either too slow or too approximate, and that limits how quickly we can evaluate candidates and close the loop with experiments. You will build the next generation of simulation methods: fast, accelerator‑native, and grounded in rigorous physics. Your work will directly expand what’s computationally tractable, letting us ask questions about molecular systems that were previously too expensive to answer. This is foundational infrastructure for everything CuspAI does.

What You Will Do

• Simulation Methodology & Tooling
  • Design and implement high‑performance simulation software in JAX, targeting GPU/TPU‑accelerated molecular and continuum‑scale methods
  • Develop surrogate models and ML‑driven acceleration techniques for physics‑based simulations
  • Build robust, reusable foundation blocks to enable the broader team to iterate rapidly on new scientific problems
• Multiscale Methods
  • Bridge molecular simulations (MD, Monte Carlo) with continuum‑level PDE models, enabling true multiscale workflows
  • Develop and refine ML‑driven enhanced sampling techniques for challenging molecular systems
  • Conduct fundamental research on developing novel Machine Learning models for coarse‑graining molecular data and extracting key parameters for higher‑scale simulations
• Research & Collaboration
  • Work closely with domain scientists across the organization to ground methods development in real project needs
  • Contribute to the scientific direction of the simulation team, identifying high‑impact methodological gaps
  • Translate research advances into production‑quality code

Must Have Skills and Qualifications

• You are motivated by the opportunity to build foundational tools that unlock new capabilities in molecular and materials science
• Demonstrated technical excellence in both research and implementation; you write high‑quality, performant code, not just papers
• Exceptional coding skills with a strong command of modern software engineering practices down to compilation level
• Deep experience with GPU/TPU‑accelerated frameworks (e.g., JAX, PyTorch) for scientific or high‑performance computing applications
• PhD (or comparable experience) in a relevant quantitative field (physics, applied mathematics, computational science, machine learning, or similar) with a strong computational mathematics foundation and the ability to apply them to physical systems
• Strong understanding of modern ML, particularly as applied to scientific problems

Bonus Points (But Not Critical)

• Background in sampling methods (MCMC, molecular dynamics) and statistical mechanics
• Experience with molecular simulation packages or developing simulation software
• Familiarity with multiscale modeling approaches or surrogate/emulator methods for PDEs
• Track record of published research at top venues in ML, computational physics, or related fields
• Hands‑on experience bridging mathematical formulations with efficient low‑level implementation, including optimizing at the compiler/CUDA level

Additional Considerations

This role could be based in Amsterdam, Berlin, Cambridge or London, with the expectation of being in the office three days per week. Additionally, there may be regular travel required to other locations for collaboration and project work.

What we offer

• A competitive salary plus equity package so you have a stake in the success of the company
• 28 days holiday
• Professional development budget for scientific conferences and technical training
• Opportunity to work at the forefront of AI‑driven scientific discovery with world‑class researchers
• Direct impact on advancing materials science through cutting‑edge technology
• Collaborative environment bridging AI research, computational chemistry, and experimental science

Equal Opportunities and Diversity Statement

CuspAI is an equal opportunities employer committed to building a diverse and inclusive workplace. We do not discriminate on the basis of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy or related condition (including breastfeeding), veteran status, or any other basis protected by applicable law. We actively encourage applications from all backgrounds and value the unique perspectives and contributions that diversity brings to our team. Please let us know if you require any specific adjustments during or after the interview process. We will do everything we can within reason to accommodate.