About Me

I am a researcher and CS PhD candidate at the University of Maryland, College Park, where I am advised by John Dickerson. My research interests include: sequential and combinatorial decision‑making under uncertainty (i.e., multi‑armed bandits, reinforcement learning, LLM‑informed agents and controllers), algorithmic fairness, and knowledge representation and reasoning. The central questions that guide my work include: (1) How can we make better decisions in the face of uncertainty and in the presence of potentially conflicting objectives, such as welfare maximization and individual or sub-group fairness? (2) How can we take advantage of semantic and/or structural information that connects our decision points or observations (e.g., to one another or to prior knowledge), and recover such information when it is partially observable?

Prior to UMD, I completed my MS in Computer Science with a concentration in Machine Learning at Georgia Tech while working as a research scientist at the Georgia Tech Research Institute. I completed my undergraduate studies at Georgetown University, and have several intervening years of professional experience in quantitative research, with a domain focus on economics and healthcare.

During my PhD, I’ve had the opportunity to intern at Amazon Robotics, where I worked on graph-based deep RL, as well as at Microsoft Research in the Fairness, Accountability, Transparency, and Ethics in AI (FATE) group, where I was mentored by Miro Dudík and Alexandra Chouldechova, and worked on statistical techniques for disaggregated model evaluation. I was also a student researcher on the Responsible AI team at Google Research, where I worked at the intersection of causal modeling and sequential decision-making to evaluate and improve algorithmic fairness in dynamic environments. Most recently, during the summer of 2023, I interned at Microsoft Research in the Augmented Learning and Reasoning group, where I was mentored by Adith Swaminathan and Jennifer Neville and worked on cost-aware uncertainty reduction and preference elicitation in chat-based recommender systems.

Outside of research, I love spending time in nature, long-distance running, learning new languages, trying (but often failing, if we’re being honest) to train my dog, and thinking about how to improve patient-physician communication and reduce time to diagnosis for patients with complex diseases. I am excited to work with new collaborators and help make CS a more inclusive field where people from all backgrounds feel welcome: please consider me a resource and don’t hesitate to reach out.