I am currently an Applied Scientist at Thomson Reuters Labs, where I am working on improving our RAG components, particularly the passage re-ranking. Previously, I was a Data Scientist at Capital One, where I was a technical lead focused on training and deploying LLMs for customer call understanding. Recently, I have led publications in COLING and EMNLP. Prior to working as a Data Scientist in industry, I worked in the Physics Department at Duke. I went to graduate school at Caltech, where I earned a PhD in Materials Science researching glassy materials and their mechanics. I love complex networks: from wooden puzzles and grains of sand, to glasses and neural networks. What these diverse subjects have in common is their ability to remember. Piles of sand, just like our brains and neural networks can have a memory of the past through their complex fabric of contacts!
