Hi! I am a machine learning engineer and researcher, and a professional content and technical writer. I am currently pursuing a JD at Arizona State University’s Sandra Day O’Connor College of Law and a PhD in Computer Science from the University of Wisconsin, Madison. I received a M.S. in Biomedical Data Science from the University of Wisconsin, Madison and a B.A. in Applied Mathematics from the University of California, Berkeley. During my M.S., I was lucky to be advised by Professors Anthony Gitter and Fred Sala, both of whom have had an outsized impact on my development as a researcher. My current academic research focuses on applying tools from differential geometry, manifold theory, and pure mathematics more generally to problems in machine learning and drug discovery. I am interested in a variety of topics including deep learning, natural language processing, computational biology, and drug discovery. I am also interested in the intersection of law and technology, particularly patent and intellectual property law surrounding generative AI as well as AI regulation and its policy implications.
In addition to my academic interests, I enjoy running, cycling, brazilian jiu-jitsu, playing guitar, piano, and drums, writing creative fiction, and reading great books. In particular, writing is a huge passion of mine. I work part-time as a professional content and technical writer specializing on machine learning, so please contact me if you are looking for a skilled writer for your software or ML business.
Juris Doctor (JD) - In Progress, 2027
Arizona State University
MS in Biomedical Data Science, 2023
University of Wisconsin, Madison
BA in Applied Mathematics, 2017
University of California, Berkeley
In this work we introduce Graph Retrieval-Optimized Generation (GROG), a method for reducing LLM hallucinations in contexts where external, graph-structured knowledge is available. We test our method on retrieval and generation tasks conditioned on publicly-available USPTO patent data and show promising results, suggesting that this method warrants further study in more diverse legal contexts and downstream applications.