Senior Research Scientist - AI Safety
This role involves leading high-impact AI safety research, focusing on red teaming and evaluations for frontier models in high-risk domains like cybersecurity and CBRN. The scientist will drive research from concept to publication, shape safety strategies, and collaborate with government and commercial partners on mitigating misuse risks. Work includes technical leadership in language models, generative AI, and robustness, with a strong emphasis on real-world deployment and policy-relevant insights.