4 months ago
Berlin, Germany +3 moreSenior
Responsibilities
- Train, fine-tune, and distill machine learning force fields.
- Research and develop machine learning force field architectures for production simulation workloads.
- Integrate models into public and in-house high-performance simulators.
- Develop distributed training and inference architectures for large-scale training, data generation, and simulation.
- Scale workloads across compute infrastructure using Ray.
- Build modular components that can be reused across different chemistry applications.
- Develop active learning systems connecting simulation, data generation, and training.
- Create interfaces that domain scientists can use and extend.
- Collaborate with computational chemists on density functional theory data generation and validation.
Requirements
- Demonstrated technical excellence in both research and implementation, including a record of building high-quality, performant systems.
- Exceptional coding skills and 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 such as Computer Science, Physics, Applied Mathematics, Computational Science, or Machine Learning.
- Strong foundation in computational methods and explicit interest in applying AI to materials science and chemistry.
- Experience with deploying, training, or modifying machine learning force fields is beneficial but not required.
- Experience managing atomistic data, density functional theory, molecular simulation methods such as MCMC or MD, graph neural network design, cloud infrastructure, or Kubernetes is beneficial.
- Published research at top-tier ML or computational physics venues such as NeurIPS or ICML is beneficial.
Benefits
- Based in Cambridge, London, Amsterdam, or Berlin with an expectation of working in the office three days per week.
- Regular travel to other locations may be required for collaboration and project work.
- Equity in CuspAI.
- 28 days of holiday in Germany, the Netherlands, and the UK, or 21 days in Japan, Singapore, and the US, plus local public holidays.
- Paid parental leave of 26 weeks for primary caregivers and 12 weeks for secondary caregivers.
- Professional development budget.
- Collaborative interdisciplinary work across AI research, computational chemistry, and experimental science.