UC Berkeley
Victoria KrakovnaSenior Research Scientist · Google DeepMindResearcher↗
Researcher
Rohin Shah
Google DeepMindLead, AGI Safety & Alignment
Shah helped develop methods for inferring human preferences from how people have shaped their surroundings.[1] He created the Alignment Newsletter[2] and co-authored DeepMind’s AI Control Roadmap, which sets out how to monitor and constrain advanced AI agents even when they do not reliably follow human intentions.[3]
Career & education
Current roleGoogle DeepMind2020-presentLead, AGI Safety & Alignment
Google DeepMind2020-presentEducation
Work 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.
citations11,522As of Jun 15, '26
citations+6,261Since last snapshot, Aug 25, '25
References
- Preferences Implicit in the State of the Worldarxiv.org
Original coauthored work learns preferences from the state of an environment shaped by people.
- Rohin Shah — personal biographyrohinshah.com
First-person research overview and Alignment Newsletter authorship.
- Google DeepMind — AI Control Roadmapdeepmind.google
Shah-coauthored June 2026 account describes monitoring, constraints and layered defenses for potentially misaligned agents; research-author list explicitly includes Shah.
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 24, 2026 · Checked for accuracy and new information.
