MLFF Distillation and GCMC Integration Internship
CuspAI is an AI-for-science company developing an AI platform for targeted materials discovery.
Funding history
About CuspAI
CuspAI combines generative AI, high-fidelity simulation, synthesis planning, and laboratory validation to develop novel materials for applications including semiconductors, energy, water purification, and climate technology.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will distill machine learning force fields into fast potentials for Monte Carlo simulations and integrate them into the simulation framework. You will curate datasets, run validation campaigns, optimize pipeline throughput, benchmark model trade-offs, collaborate on reference data and validation, and contribute to a publication.
Requirements
- Current or recently completed PhD or Master's programme in a relevant quantitative field
- Experience in atomic-scale adsorption modelling
- Hands-on experience with GCMC, MD, or both
- Comfort working in Linux environments and managing simulation campaigns at scale
- Interest in applying ML to chemistry and materials science
Responsibilities
- Distill MLFFs into fast student potentials for Monte Carlo simulations
- Curate, version, and document training and validation datasets
- Run validation campaigns against classical force-field baselines
- Profile and optimize pipeline throughput in the Monte Carlo inner loop
- Benchmark accuracy and speed trade-offs and document model failures
- Collaborate on reference-data generation, benchmark selection, and validation strategy
- Contribute to a publication on MLFF-driven GCMC for MOF screening
Benefits
- Equity in CuspAI
- 28 days holiday in Germany, the Netherlands, and the UK, or 21 days holiday in Japan, Singapore, and the US, plus local public holidays
- 26 weeks of fully paid parental leave for primary caregivers and 12 weeks for secondary caregivers
- Professional development budget