Cornell University
Johns Hopkins University
IIT Kanpur
The University of Texas at Austin
Evan HubingerMember of Technical Staff, Manager · AnthropicResearcher↗
Researcher
Sandipan Kundu
AnthropicMember of Technical Staff
Kundu moved from theoretical physics into model alignment at Anthropic. He helped develop Constitutional AI, which trains assistants using written principles and AI feedback, and studies how specific those principles should be, whether reasoning traces are faithful and how long contexts enable jailbreaks.
Career & education
Current roleAnthropic2022-presentMember of Technical Staff
Anthropic2022-presentWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations11,338As of Oct 11, '26
citations+2,614Since last snapshot, Jun 15, '26
Selected contributions
Constitutional AI: Harmlessness from AI Feedback
With Yuntao Bai, Saurav Kadavath, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie and others ·Trained AI assistants to critique and improve their answers using a written set of principles.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 9, 2026 · Checked for accuracy and new information.
