Postdoctoral Research Assistant in Machine Learning
University of Oxford, United Kingdom
- Institution
- University of Oxford
- Country
- United Kingdom
- Position type
- Postdoc
- Subject area
- Computer Science & AI
- Salary
- GBP 39424.00–47779.00 YEAR
- Location
- Oxford, England, United Kingdom
- Funding
- Fully funded position
Want to be the strongest applicant for this position?
Book a free 15-minute call with our team. We will look at your profile against what University of Oxford is actually looking for, and tell you honestly where you stand and what to strengthen before you apply.
Book a free call about this position →No cost, no obligation. Mentors who have secured funded PhD positions themselves.
How our PhD admission mentorship works →
We mentor STEM applicants only. If your research aspirations are outside STEM subjects, you're very welcome to use this board and apply directly; we just aren't the right people to mentor you.
About this position
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 the safety, 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 be agentic safety, adversarial robustness, and AI control. This includes agent hijacking, prompt injection, adversarial manipulation, unsafe tool use, oversight evasion, and transferable 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 adel.bibi@eng.ox.ac.uk
For more information about working at the Department, see www.eng.ox.ac.uk/about/work-with-us/
Only online applications received before midday on the 9 October 2026 can be considered. You will be required to upload a covering letter/supporting statement, including a brief statement of research interests (describing how past experience and future plans fit with the advertised position), CV and the details of two referees as part of your online application.
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
Apply directly to University of Oxford
Emerging Scholars Council is not the employer and does not recruit for this position. It is advertised by University of Oxford, and your application goes to them. We help students prepare and strengthen their applications.
Go to the official application page →Contact listed in the advert
Some positions — especially in Germany, Austria and Switzerland — are filled by writing directly to the supervisor rather than through an online form. These addresses were taken from the advert text, so check them against the official listing before you write.
A cold email to a supervisor is the highest-leverage thing you can send — and the easiest to get wrong. Ask us to look at yours before you hit send.