
Rohin ShahResearcher
Google DeepMind
Lead, AGI Safety & Alignment
via Google DeepMind
Researcher · Founder

Senior Research Scientist at Google DeepMind
Co-founder at Future of Life Institute
Krakovna is an influential AI-safety researcher known for studying how advanced systems can pursue unintended goals, behave deceptively, or exploit flaws in their instructions. She co-founded the Future of Life Institute and researches AI alignment at Google DeepMind.
See something inaccurate or outdated?
Google DeepMind
Future of Life Institute
Google DeepMindWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.