B.Sc. in Computer Science, The University of Chicago.
I'm a third-year CS PhD at The University of Illinois-Urbana Champaign, advised by Prof. Tianyin Xu.
I work on AI for System Reliability Engineering: I design system-side frameworks and tooling support to make agentic systems more reliable.
LLM-powered coding agents have fundamentally changed engineering workflows in software development. However, on the System Reliability Engineering side, LLM agents have achieved little successes so far. System Reliability Engineering tasks, such as incident management and cluster maintenance, require a substantially different set of capabilities that current agents and agentic systems lack. Moreover, the nondeterministic behavior of LLMs can have catastrophic effects on production systems. My research focuses on building high-fidelity benchmarks to evaluate how prepared LLM agents are for System Reliability Engineering tasks, as well as developing agent frameworks that enable them to operate cloud clusters and distributed systems more reliably.
My research has culminated in SREGym, a live SRE benchmark with high-fidelity SRE incidents to evaluate SRE agent's incident diagnosis and mitigation capabilities, and Stratus, a multi-agent systems that enables autonomous SRE incident management through a transaction-like semantics, and previously, HotGPT, trying to understand the edges and limits of LLMs before time.
A short bio can be found here.
I'm extremely fortunate to be able to mentor and work with these students.
Unless specifically noted, I do not own any of the images presented on this site. All rights go to their respective owner.
My past life... here