Research Scientist, Harmful Manipulation & AI Safety

DeepMind is seeking a Research Scientist in the Harmful Manipulation domain within the ReDI team. You will research emerging risks in harmful manipulation, develop evaluations, and publish methodologies to impact model development and governance. The role bridges research and practice across global teams and interacts with external stakeholders.

The role emphasizes safety, ethics, and collaboration with cross-functional teams to inform mitigation strategies and governance decisions.