systems • agents • tooling
Built a real-time simulator for satellite telemetry and orbital passes with a station dashboard to display live connections and data. Powered by TiDB for storage and deployed with Docker, Kubernetes, and Helm in the XLab. Practiced fault injection, monitoring, and resilience testing.
Developed a swipe-to-save app with Firebase authentication and OpenAI embeddings to filter RSO and lab cards. Scraped UIUC CS and RSO sites with BeautifulSoup and Cheerio to build the dataset.
Published Chrome extension that overlays YouTube with AI-generated summaries and quizzes using scraped transcripts. Built with LangChain pipelines and the OpenAI API to help students study more efficiently.
Published.
hands-on builds • shipped features • real users
Built production features across the stack; focused on ops tooling, UX flows, and cloud deploys.
Developed an internal chatbot that processes over 1,500 technical PDFs–including 400+ page manuals and engineering drawings–to assist the maintenance team, reduce downtime, and link directly to exact pages in source documents.
Created a Microsoft Teams bot that makes SQL queries and outputs PowerBi Dashboards
Implemented a full-stack application for data entry for Autopour and Melting machines.
Created a Downtime dashboard to visualize downtime across machines, enabling filtering by machine and date.
In XLab’s Site Reliability Engineering research lab, I design and evaluate systems that make cloud infrastructure more resilient. I began by building observability tools that let agents interpret real metrics and traces, and I am now developing a benchmarking framework and fault injection experiments to study how autonomous agents can detect and mitigate failures in distributed databases and Kubernetes operators.
Tool-calling tasks with post-tool hooks; Prometheus/Jaeger metrics and traces.
Kubernetes & Docker–based orbital simulation app, fault injection, holographic controls.