Internship - MLFF Distillation & GCMC Integration

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.

We’re on the cusp of the on-demand materials era. Join us.

We are seeking an intern for a 3-month internship to develop fast, accurate machine learning force fields (MLFFs) tailored to high-throughput Monte Carlo simulation, and integrate them into our in-house simulation framework, kUPS. You will be embedded in our chemistry team and work closely with CuspAI colleagues.

Note: You would be joining as an engineering intern within the chemistry team at CuspAI.

You will deliver one of the foundational capabilities our simulation stack needs to evaluate the next generation of MOFs: an MLFF that is both accurate enough to replace classical force fields for guest–host interactions and fast enough to run inside the inner loop of GCMC. By distilling state-of-the-art equivariant models into a lightweight student potential and integrating the result directly into kUPS, you will expand what is computationally tractable for CuspAI and the wider gas adsorption community.

Models

• →

  Distill MLFFs into fast student potentials optimised for Monte Carlo simulations.

• →

  Curate, version, and document training and validation datasets, including the distillation protocol and any active-learning loops used to close coverage gaps.

Integration & Validation

• →

  Run head-to-head validation campaigns comparing the distilled MLFF against classical force-field baselines across a curated set of guest molecules, characterising accuracy, throughput, and failure modes.

Systems & Infrastructure

• →

  Profile and optimise the pipeline for throughput, with particular focus on the MC inner loop where MLFF inference cost dominates.

• →

  Benchmark accuracy/speed trade-offs systematically and document where the distilled model fails.

Science & Collaboration

• →

  Collaborate with computational chemists on reference data generation, benchmark system selection, and validation strategy.

• →

  Contribute to a publication establishing MLFF-driven GCMC for MOF screening.

• Currently enrolled in (or recently completed) a PhD or Master's programme in a relevant quantitative field (Physics, Chemistry, Chemical Engineering, Computational Science, Machine Learning, or similar).

• Experience in adsorption modelling at the atomic scale.

• Hands-on experience with molecular simulation methods (GCMC, MD, or both).

• Comfortable working on Linux environments and managing simulation campaigns at scale.

• A genuine interest in the application of ML to chemistry and materials science.

• Familiarity with modern MLFFs.

• Experience with knowledge distillation or other model compression techniques for scientific ML.

• Experience with active learning workflows for atomistic data.

• Familiarity with DFT data generation and the practicalities of curating atomistic datasets.

• Direct experience with established simulation packages.

• Background in gas adsorption, MOFs, or porous materials.

• Familiarity with classical force fields used in MOF simulation.

• A track record of published research at top-tier ML or computational chemistry venues.