Our group develops new machine learning and physics-based methods to model, understand, and design molecular systems across scales. We work on topics ranging from ML-augmented molecular simulations and generative models for novel materials design to concurrent multiscale simulation, coarse-graining, uncertainty quantification, and scalable software. By combining methodological innovation with applications in nanoscale science and atomistic material design, we aim to create computational tools that make molecular models more accurate, efficient, and predictive. Read more
If you are excited by the idea of combining physics, chemistry, machine learning, and computation to solve challenging problems, our group offers the opportunity to work on cutting-edge research and grow as an interdisciplinary scientist. See open positions.