I lead technical safety at Microsoft AI’s Superintelligence organization, where my team is responsible for safety evaluations, post-training, and deployment mitigations for frontier models and agents. Previously, I led AI safety at Inflection AI and spent several years building machine learning systems for platform manipulation at Twitter and malware and fraud detection in the cybersecurity industry.

I write about AI safety, security, and trust at No Failsafe and am the co-author of Introduction to Generative AI.

I currently live in Brooklyn, New York with my husband and daughter.