I am a research scientist at Google working on RAG, LLM distillation, and post-training. Previously, I spent two years at AWS AI labs leading research in open-domain QA, LLM evaluations, and alignment while building AWS enterprise AI assistant services Kendra and Amazon Q.

I earned my computer science Ph.D. degree from the University of Southern California, where I was advised by Prof. Nanyun Peng and Prof. Aram Galstyan. My doctoral thesis proposes novel machine learning models/datasets for event-centric reasoning with applications in information extraction, question answering and language generation.

Prior to joining USC, I worked as a statistical researcher and a data scientist for more than three years. While working full-time, I obtained an M.Sci. degree in data science at NYU where I had the privilege to work with Prof. Kyunghyun Cho.