Applied ML Researcher (Force Fields and Simulation)

# ML Research Engineer (Machine Learning Force Fields)

Role: Member of Technical Staff

## Your Impact
You'll shape the simulation infrastructure that enables CuspAI to evaluate novel material candidates through atomistic physics. You'll bring these simulations to the accuracy and performance needed to power large-scale search campaigns, and design them to be flexible and versatile so they can be adapted quickly to new challenges.

## What You Will Do

### Models

• Train, fine-tune, and distill machine learning force fields
• Research and develop novel ML force field architectures suited to production simulation workloads

### Systems & Infrastructure

• Integrate these models into public and in-house high-performance simulators
• Develop training and inference architectures for large-scale training, data generation, and simulation
• Distribute these workloads via Ray to scale across compute infrastructure
• Build the system with modularity in mind, so components can be reused across many kinds of chemistry

### Science & Collaboration

• Build an active learning system that closes the loop between simulation, data generation, and training
• Develop interfaces that make the system easy for domain scientists to use and extend
• Collaborate closely with computational chemists on density functional theory (DFT) data generation and validation

## Must Have Skills and Qualifications

• Demonstrated technical excellence in both research and implementation; track record of building high-quality, performant systems
• Exceptional coding skills with strong command of modern software engineering practices
• Deep production or research experience with distributed machine learning systems
• PhD (or comparable professional experience) in a relevant quantitative field (Computer Science, Physics, Applied Mathematics, Computational Science, Machine Learning) with strong foundation in computational methods
• Genuine and explicit interest in the potential applications of AI within materials science and chemistry

## Bonus Points

• Experience with deploying, training, and modifying machine learning force fields
• Experience with management of atomistic data
• Experience with Density Functional Theory
• Experience with molecular simulation methods (MCMC, MD)
• Experience with graph neural network design
• Experience with Cloud infrastructure and Kubernetes
• Track record of published research at top-tier venues in ML (NeurIPS, ICML) or computational physics

## Location and Work Arrangement
Role could be based in Cambridge, London, Amsterdam, or Berlin offices, with expectation of being in the office three days per week. May require regular travel to other locations for collaboration and project work.