I am an incoming Assistant Professor at [university to be announced]. My research goal is to build systems and interfaces for data-intensive knowledge work. We take a "full stack" approach: we build open-source software, deploy it in real applications, and use what we learn to advance research in systems, interfaces, and user behavior.

Current Research Projects

• Efficient LLM-powered data analysis
• Agents for messy data workflows
• AI-native writing apps

I (am close to having) received my PhD in EECS from UC Berkeley's Data Systems and Foundations group, advised by Aditya Parameswaran. In my PhD, I designed and built the DocETL and DocWrangler ecosystem for scalable LLM-powered data processing. I also wrote several papers, a course, and a book on evaluating LLM-powered applications. Our work has had real-world impact in (1) databases, e.g., Snowflake, BigQuery; (2) AI tooling, e.g., LangChain, ChromaDB, OpenAI; and (3) society, DocETL powers a tool helping California public defenders challenge wrongful convictions under the Racial Justice Act.