CS547 Human-Computer Interaction Seminar   (Seminar on People, Computers, and Design)

Fridays 11:30am-12:30pm PT · Gates B3 · Open to the public
Previous | Next
Aditya Parameswaran
UC Berkeley
Rethinking the Role of Humans in LLM-Powered Data Systems
October 30, 2026

We are witnessing some of the biggest changes to data systems in decades thanks to AI, bringing vast volumes of unstructured data, such as documents, video, and images, within reach. At Berkeley, we have been building data systems with LLM-powered operators for querying and analyzing unstructured document collections. Our open-source work in this space has been adopted across sectors, including by 30 companies in the S&P 500. In this talk, I will describe the design of these systems, focusing on the human perspective: how people author LLM-powered data pipelines when they can't fully specify what they want up front, and how systems can help them understand, debug, steer, and ultimately trust LLM outputs at scale.


Aditya Parameswaran is an Associate Professor in EECS at UC Berkeley and a co-director of the EPIC Data Lab. Aditya also leads research efforts on AI and data systems at Snowflake. Aditya has published 100+ papers overall at top venues across DB, HCI, and AI, with multiple paper recognitions in each area. Multiple open-source tools developed in his group have received thousands of GitHub stars (including Modin, Lux, IPyFlow, DocETL) and have been downloaded tens of millions of times overall across a spectrum of industries. His research was commercialized as a startup, Ponder, in 2021, where he served as Co-founder and President, before its acquisition by Snowflake in 2023. Aditya has received the Alfred P. Sloan Research Fellowship, TCDE Ten Year Influential Paper award, VLDB Early Career Award, SIGMOD Best Paper Award, NSF CAREER Award, the TCDE Rising Star Award, along with other recognitions. His website is at http://adityagp.net.