Research Engineer · CS @ UIUC · AI + Systems + SRE
I build the infrastructure that teaches AI to resolve real-world production failures. Core team @ SREGym, a high-fidelity, interactive benchmark for AI Site Reliability Engineering, with a paper accepted at CAIS '26 and active adoption at Microsoft Research, Resolve AI, and the University of Washington. Supported by a Slingshot grant from the Laude Institute.
SREGym and my research have been recognized by academia and industry.
"SREGym: A Live Training Ground for AI SRE Agents with High-Fidelity Failure Drills" was accepted at CAIS '26, a premiere new ACM venue dedicated to AI agents research, co-located with leading systems conferences.
The Siebel School highlighted SREGym for its novel approach to evaluating AI SRE agents against real production failures in live cloud environments.
Read Article ↗Adopted by top researchers and commercial agentic SRE platforms, Resolve AI's production observability controller drops into a SREGym cluster with a single kubectl command, validating the framework as a drop-in evaluation harness for industry-grade AI SRE tooling.
Enabled misoperation as a new fault class in SREGym by porting TiDB and building a new application on top, expanding the benchmark's fault coverage into a previously unexplored category.
Built Model Context Protocol tools for the LangGraph agent, Prometheus server with PromQL querying and Jaeger trace tools, so agents can query live metrics and distributed traces during incident resolution.
Created a tool that converts JSONL agent outputs into readable, timestamped HTML reports, making evaluation workflows faster and more legible for the entire research team.
Interactive terminal UI in Go using Bubble Tea for dynamic fault injection and application deployment, a keyboard-driven dashboard for triggering failure drills and managing cluster deployments.
Automated benchmark runner distributing SREGym problems across multiple nodes, handles cluster creation, parallel tmux execution, and auto log collection. Adding nodes directly reduces per-node problem load.
Beyond SREGym, internship work and personal projects that shipped to real users.
2025 Siebel Celebration of Excellence
Recognized twice by the Siebel School of Computing & Data Science for academic excellence and research impact in the same year.
James Scholar & Scholarships
Grainger College of Engineering distinguished scholar and recipient of two competitive merit scholarships for academic performance and leadership.
Dean's List
UIUC Grainger College of Engineering Dean's List for three consecutive semesters, maintaining a 3.97 GPA in Computer Science.
Salutatorian
Graduated 2nd of 570 students at Highland Park High School. GPA: 4.66 weighted, 3.99 unweighted.
Polish School Red Ribbon Graduate
Earned the Red Ribbon academic distinction every year from middle school through high school, the highest honor at Polish School.
B.S. Computer Science · Dean's List (3×) · James Scholar
Coursework: Data Structures · Computer Architecture · Discrete Structures · Linear Algebra with Computational Application · Probability & Statistics for CS · Software Engineering Lab · Systems & Networking Seminar
Salutatorian (2nd of 570 students) · Chamber of Commerce Scholarship
Invited to join a selective program connecting with NVIDIA engineers and alumni, with exposure to GPU computing, AI tooling, and professional development.
Current and completed courses.