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.
More from Companies & People
- OpenAI data trainers reportedly fired for using AI to do their AI-training job — CackleRooster · 2026-09-22
- Healthcare AI Weekly: 100+ experts call for third-party evaluators as sector consolidation begins — HealthcareAIGuy · 2026-09-22
- Wayve and Mercedes sign global deal to bring AI Driver to production cars in two years — alexgkendall · 2026-09-22
- Agency Founder Exits Six-Year, Multi-Million-Dollar Creme Digital to Go All-In on AI — damienghader · 2026-09-22
- OpenAI contractors fired for using AI to train the AI, 404 Media reports — 404 Media · 2026-09-22
- Andreessen Horowitz invests $35M in an unaccredited college alternative — KateClarkTweets · 2026-09-22