I’m a Senior Research Scientist at Microsoft and UC Berkeley. My goal is to build safe, intelligent agents that make decisions in the open world using planning, RL, and LLMs. To do this, I develop formal/empirical approaches to decision making in intelligent agents, focusing on AI assistants, self-driving cars, humanoid robots, and planetary rovers.
Before that, I completed my PhD in Computer Science under Shlomo Zilberstein in the Resource-Bounded Reasoning Lab at UMass Amherst. My dissertation introduced a range of metareasoning techniques that optimize—particularly monitor and control—the planning and execution processes that compose intelligent agents.
Recently, I’ve won a Distinguished Paper Award at AAAI, received an NSF Graduate Research Fellowship, and was a Distinguished Teaching Award Finalist at UMass Amherst.
-
Marist College
BS in Computer Science and Philosophy
4.0 — Valedictorian — NSF Technology Full Scholarship
-
UMass Amherst
MS/PhD in Computer Science
4.0 — PhD Candidate with Distinction — NSF Graduate Research Fellowship
News
“I joined Microsoft as a Senior Research Scientist.”
“I’ll be co-organizing the IROS Workshop on Building and Evaluating Ethical Robotic Systems.”
“I co-organized the CHAI Workshop on AI safety.”
“We released an arXiv paper that introduces a new LLM jailbreak dataset.”
“ICLR accepted our paper that introduces a prompt injection dataset from our LLM game Tensor Trust.”
“Our paper on the online LLM game Tensor Trust received Honorable Mention at ITIF at NeurIPS.”
“ITIF at NeurIPS accepted our paper that introduces a prompt injection dataset from our LLM game Tensor Trust.”
“We released an arXiv paper that introduces active teacher selection in RLHF.”
“I transitioned into a Research Scientist with Stuart Russell at UC Berkeley.”
“I co-organized the CHAI Workshop on AI safety.”
“We released an arXiv paper that surveys the intersection of fairness and sequential decision making.”
“Our paper on active reward learning from multiple teachers was a Best Paper Award Finalist at SafeAI at AAAI.”
“AIJ accepted our article that introduces competence-aware systems.”
“I started a postdoctoral fellowship under Stuart Russell at UC Berkeley.”
“I defended my dissertation.”
“I co-organized the IROS Workshop on Building and Evaluating Ethical Robotic Systems.”
“Our paper on ethically compliant sequential decision making won a Distinguished Paper Award at AAAI.”
“ECAI accepted my doctoral consortium paper that outlines my dissertation on metareasoning.”
“DynamicSlam at ICRA accepted our paper that introduces agent-aware state estimation.”
“I was a finalist for the Distinguished Teaching Award for teaching assistants.”
“I passed my PhD candidacy qualifier exam with distinction.”
“I’m the primary inventor on a patent for self-driving cars.”
“My advisor and I were awarded an NSF Grant on Robust Intelligence.”
“I was awarded an NSF Graduate Research Fellowship.”