MLFF Distillation & GCMC Integration Intern

CuspAI; Cambridge; On-site; GBP 25,000 - 32,000; Part time

Benefits offered by this job

Equity in company

28 days holidays (UK)

Parental leave (Gold Standard)

Professional development budget

Meaningful, interdisciplinary work

Job summary

CuspAI is seeking an engineering intern to develop fast, accurate ML force fields (MLFFs) tailored to high‑throughput Monte Carlo simulation and to integrate them into our in‑house framework, kUPS. You’ll be embedded in the chemistry team, working with world‑class researchers to push the boundaries of materials science using ML.

You will distill state‑of‑the‑art equivariant models into lightweight potentials, curate datasets, and run validation campaigns to ensure accuracy and speed for

Qualifications

• PhD or Master’s in a quantitative field (physics, chemistry, chemical engineering, computational science, ML).
• Experience in adsorption modelling at atomic scale.
• Hands-on experience with molecular simulation methods (GCMC, MD).
• Comfortable working on Linux environments and managing simulation campaigns at scale.
• Genuine interest in applying ML to chemistry and materials science.

Responsibilities

• Distill MLFFs into fast student potentials optimised for Monte Carlo simulations.
• Curate, version, and document training/validation datasets and distillation protocol.
• Run head-to-head validation campaigns vs classical baselines to characterise accuracy and throughput.
• Profile and optimise the pipeline for MC inner loop throughput and document failure modes.
• Collaborate with computational chemists on data generation and validation strategies.
• Contribute to a publication establishing MLFF-driven GCMC for MOF screening.

Skills

Adsorption modelling

Molecular simulation (GCMC/MD)

Linux environments

ML for chemistry/materials

Education

PhD or Master’s in a quantitative field

Tools

GCMC/MD simulation packages

Job description

CuspAI is seeking an engineering intern to develop fast, accurate ML force fields (MLFFs) tailored to high‑throughput Monte Carlo simulation and to integrate them into our in‑house framework, kUPS. You’ll be embedded in the chemistry team, working with world‑class researchers to push the boundaries of materials science using ML.

You will distill state‑of‑the‑art equivariant models into lightweight potentials, curate datasets, and run validation campaigns to ensure accuracy and speed for