MLFF Distillation & GCMC Integration Internship

About the role

We are seeking a 3‑month intern to develop fast, accurate machine‑learning force fields (MLFFs) for high‑throughput Monte Carlo simulations and integrate them into our in‑house simulation framework, kUPS, within the chemistry team at CuspAI.

Key responsibilities

• Distill state‑of‑the‑art equivariant MLFF models into lightweight student potentials optimized for Monte Carlo simulations.
• Curate, version, and document training and validation datasets, including active‑learning loops to close coverage gaps.
• Run head‑to‑head validation campaigns against classical force‑field baselines, characterising accuracy, throughput and failure modes.
• Profile and optimise the simulation pipeline, focusing on the inner Monte Carlo loop where inference cost dominates.
• Collaborate with computational chemists on reference data generation, benchmark selection and validation strategy, and contribute to a publication on MLFF‑driven GCMC for MOF screening.

Required profile

• Currently enrolled in or recently completed a PhD or Master’s program in Physics, Chemistry, Chemical Engineering, Computational Science, Machine Learning or a related quantitative field.
• Experience in adsorption modelling at the atomic scale.
• Hands‑on experience with molecular simulation methods such as GCMC or MD.
• Comfortable working in Linux environments and managing large‑scale simulation campaigns.
• Strong interest in applying machine learning to chemistry and materials science.

Required skills

• Adsorption modelling
• GCMC and/or MD simulation
• Linux operating system
• Simulation campaign management
• Machine‑learning for chemistry

What we offer

• Competitive salary and equity in CuspAI.
• 28 days (or 21 days) holiday plus public holidays.
• Generous parental leave (26 weeks primary, 12 weeks secondary).
• Professional development budget.
• Opportunity to work on impactful materials‑science problems in a multidisciplinary team.