Postdoctoral Research Assistant in Machine Learning

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

UK date and time: 20-September-2026 15:30

Postdoctoral Research Assistant in Machine Learning

central Oxford

We are seeking a full-time Postdoctoral Research Assistant to join Torr Vision Group at the Department of Engineering Science, central Oxford. The post is funded by Coefficient Giving and is fixed-term to the 30th June 2027.

We are seeking a highly motivated postdoctoral researcher to investigate thesafety, security, control, and capabilities of advanced AI systems, with a particular focus on increasingly autonomous and agentic models. The research will examine frontier AI systems that interact with operating systems, APIs, software tools, other agents, and complex environments, moving beyond text generation towards systems capable of planning, pursuing objectives, and executing long-horizon tasks.

A central focus will beagentic safety, adversarial robustness, and AI control. This includes agent hijacking, prompt injection, adversarial manipulation, unsafe tool use, oversight evasion, andtransferable attacks that generalise across agents, models, tasks, and environments. We are particularly interested in building agentic systems that can autonomously discover, test, and evaluate general attack strategies against other AI agents, helping identify systematic vulnerabilities rather than attacks specific to a single model or setting.

Candidates should possess a PhD (or be near completion) in PhD in Computer Science, AI, Security, or a related field. You will have a Strong background in machine learning and/or computer security and Experience working with LLMs or agent-based systems.

Informal enquiries may be addressed to [e-mail]

For more information about working at the Department, see www.eng.ox.ac.uk/about/work-with-us/

The Department holds an Athena Swan Bronze award, highlighting its commitment to promoting women in Science, Engineering and Technology

Machine Learning, AI Safety, agentic safety