Shreya Shankar
Computer science researcher who built DocETL at UC Berkeley; incoming Assistant Professor at Carnegie Mellon
Shreya Shankar is a computer science researcher who will join Carnegie Mellon University's Computer Science Department as an Assistant Professor in 2027, affiliated with the CMU Database Group. During a PhD in EECS at UC Berkeley, working with Aditya Parameswaran, Shankar built the DocETL stack for LLM-powered data processing; the DocETL repository says the system was created at Berkeley's EPIC Data Lab and Data Systems and Foundations group. Shankar is first author of the DocETL paper (2024), which proposed agentic query rewriting and evaluation for complex document processing. Shankar also co-teaches a course on AI evals with Hamel Husain and is a co-author of "What We've Learned From A Year of Building with LLMs" (2024).12345
Work
DocETL (external site: github.com)Open-source code
Built DocETL during PhD research at UC Berkeley and is first author of "DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing" (2024). The MIT-licensed repository says DocETL was created at the EPIC Data Lab and Data Systems and Foundations group at UC Berkeley.143
What We've Learned From A Year of Building with LLMs (external site: applied-llms.org)Published research
Co-author of the 2024 essay on lessons from building LLM products; the authors credit Shankar with bringing research and original results on evals and production practices.5
Other documented roles
Roles the sources document but that are not confirmed as current.
- CS PhD student, working with Aditya Parameswaran, University of California, Berkeley (EECS)21
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.