About Me

I’m an Applied Scientist at Amazon working on learned memory, representation learning, and language models. My recent work focuses on compressing complex histories into reusable representations for retrieval, prediction, and generation. More broadly, I’m interested in how learned representations can preserve uncertainty and guide reasoning, exploration, and decision-making.

I earned my PhD in Statistics from the University of Wisconsin–Madison, advised by Professor Matthias Katzfuss. My doctoral research focused on scalable Bayesian optimization, uncertainty quantification, and approximate posterior inference.

Previously, I completed a combined B.S./M.S. in Applied Mathematics at the University of Colorado Boulder and worked in the Statistical Engineering Division at NIST. During my PhD, I interned at Microsoft Research New England and Toyota Research Institute.