2 months ago
Cambridge, United Kingdom or London, United KingdomIntern
Responsibilities
- Distill machine-learning force fields into fast student potentials optimized for Monte Carlo simulations.
- Curate, version, and document training and validation datasets, including distillation protocols and active-learning loops.
- Validate distilled MLFFs against classical force-field baselines across curated guest molecules, measuring accuracy, throughput, and failure modes.
- Profile and optimize the pipeline, especially MLFF inference in the Monte Carlo inner loop, and document accuracy-speed trade-offs.
- Collaborate with computational chemists on reference data generation, benchmark selection, and validation strategy.
- Integrate the distilled MLFF into the in-house kUPS simulation framework and contribute to a related publication.
Requirements
- Currently enrolled in or recently completed a PhD or Master’s program in Physics, Chemistry, Chemical Engineering, Computational Science, Machine Learning, or a similar quantitative field.
- Experience with adsorption modeling at the atomic scale.
- Hands-on experience with molecular simulation methods such as GCMC or MD.
- Comfort working in Linux environments and managing simulation campaigns at scale.
- Genuine interest in applying machine learning to chemistry and materials science.
- Preferred qualifications include familiarity with modern MLFFs, knowledge distillation, model compression, active learning, DFT data generation, atomistic datasets, established simulation packages, gas adsorption, MOFs, porous materials, classical force fields, or published research in ML or computational chemistry.
Benefits
- Three-month internship.
- Competitive salary and equity in CuspAI.
- 28 days of holiday in DE, NL, and UK, or 21 days in JP, SG, and US, in addition to local public holidays.
- Paid parental leave of 26 weeks for primary caregivers and 12 weeks for secondary caregivers.
- Professional development budget.
- Collaborative interdisciplinary work with AI researchers, computational chemists, experimental scientists, and engineers.