Implement Machine Learning Interaction Potentials into molecular dynamics simulation pipelines, ensuring they are robust, scalable, and optimized for High-Performance Computing (HPC) and GPU-accelerated environments
Partner closely with computational chemists and medicinal chemists to apply ML-based simulations to key drug discovery problems, such as binding affinity prediction and conformational sampling
Analyze simulation data generated by our models, providing a mechanistic understanding of molecular behavior and communicating complex results to a broad scientific audience
Stay up-to-date with the latest advancements in ML-based potentials and related fields, contributing to the scientific strategy and intellectual property of the company

Ph.D. in Computational Chemistry, Physics, or a related field with a strong focus on machine learning and molecular modeling
A minimum of 3 years of post-doctoral or industry experience developing or applying ML-based potentials
Extensive hands-on experience with deep learning frameworks and a strong understanding of neural network architectures relevant to molecular modeling
Deep theoretical and practical knowledge of molecular dynamics and classical force fields
Proficiency in programming, with expertise in Python being essential
Experience with High-Performance Computing (HPC) environments
Experience with ML-based potentials and an understanding of their underlying principles
Familiarity with quantum chemistry (QM) methods and software (e.g., Gaussian, VASP, ORCA) for generating high-quality training data
Experience with molecular dynamics simulation packages (e.g., Tinker, GROMACS, LAMMPS, OpenMM)
A track record of scientific publications or contributions to open-source software in the field of ML potentials.

Research Scientist

Key skills