Postdoc: Agentic AI Safety & Robustness Research

Corehr; Oxford; On-site; GBP 34,000 - 42,000; Full time

Job summary

University of Oxford's Torr Vision Group is seeking a full-time Postdoctoral Research Assistant to explore safety, security, and agentic capabilities of advanced AI systems in central Oxford. The role targets autonomous, planning, and long-horizon tasks with emphasis on agentic safety and robustness.

Candidates should hold a PhD in Computer Science, AI, Security or related field, with strong ML or security background and experience with LLMs or agent-based systems.

Qualifications

• PhD (or near completion) in Computer Science, AI, Security or related field.
• Strong background in machine learning and/or computer security.
• Experience with LLMs or agent-based systems.

Responsibilities

• Investigate safety, security, control and capabilities of advanced AI systems.
• Focus on agentic safety, robustness, and AI control, including transfer of attacks across agents/models.
• Work within the Torr Vision Group at Oxford to advance frontier AI research.

Skills

Machine learning

LLMs/agent-based systems

AI safety/robustness

Education

PhD in Computer Science/AI/Security or related field

Job description

University of Oxford's Torr Vision Group is seeking a full-time Postdoctoral Research Assistant to explore safety, security, and agentic capabilities of advanced AI systems in central Oxford. The role targets autonomous, planning, and long-horizon tasks with emphasis on agentic safety and robustness.

Candidates should hold a PhD in Computer Science, AI, Security or related field, with strong ML or security background and experience with LLMs or agent-based systems.