Joshua Goings

Joshua is a research associate with Xiaosong Li in the Department of Chemistry, focusing on leveraging machine learning methods (particularly reinforcement learning) to obtain compact representations of molecular wave functions. Using these optimally compact wave functions, we aim to develop quantum computing algorithms to help solve challenging chemical problems.

Previously, Joshua was a postdoctoral researcher with Sharon Hammes-Schiffer at Yale University, where he developed interpretable machine learning models for molecular dynamics. These models were used to identify crucial molecular features that predict chemical reaction dynamics in artificial photosynthesis. A long-time Pacific Northwest resident, Joshua received his PhD in theoretical chemistry in 2017 from the University of Washington, and his BS in chemistry in 2012 from Seattle Pacific University.

Joshua is also interested in using machine learning methods to help overcome computational bottlenecks along the entire quantum chemistry workflow, from finding optimal molecular geometries, to interpreting complex molecular motions, to fast generative models for molecular wave functions. He also contributes to the open-source Chronus Quantum (http://chronusquantum.org/) electronic structure package.