I am currently a machine learning scientist at Profluent Bio working on pretraining frontier protein foundation models for gene editing and antibodies. Previously, I did my Ph.D. at the GRAIL Lab and Geometric Learning Lab at Northeastern University, advised by Lawson Wong and Robin Walters. I worked on incorporating symmetries into deep learning, addressing limitations of equivariant neural networks in cases where symmetries are imperfect or unknown. I am broadly interested in how to make machine learning more efficient and generalizable, and have also worked on making imitation learning more robust with learned dynamics models, predicting complex dynamics over meshes, and on multiresolution tensor models for spatial analysis.