Oxford's Torr Vision Group hiring postdoc in agentic AI safety and control

j_foerst · x · 2026-09-22

Philip Torr's group at Oxford's Department of Engineering Science is hiring a full-time postdoctoral research assistant, funded by Coefficient Giving and fixed-term until June 30, 2027. The role focuses on safety, security, control, and capabilities of advanced AI systems — especially increasingly autonomous, agentic models that interact with OSes, APIs, tools, and other agents. Core topics: agent hijacking, prompt injection, adversarial manipulation, unsafe tool use, oversight evasion, agentic safety, adversarial robustness, and AI control.

Original post →

More from Companies & People

Companies & People channel →