Research Assistant on AI Safety

Corehr; Oxford; On-site; GBP 36,000 - 39,000; Full time

Job summary

University of Oxford's Department of Computer Science invites applications for a Research Assistant to contribute to AI safety, security, and reliability projects within the OATML group. You will work on frontier models like LLMs and multimodal foundations, under Prof Yarin Gal and Dr Lin Li.

The role requires a Master’s degree (or near completion), knowledge of foundation models, and strong programming skills.

Qualifications

• Master’s degree (or near completion) in a relevant field.
• Knowledge of foundation models (generative AI), LLM jailbreaking, safety alignment, adversarial ML, or deep learning.
• Strong programming skills.
• Ability to produce publishable research and communicate proposals and findings effectively.

Responsibilities

• Support AI safety, security, reliability research within OATML.
• Produce publishable research and present results.
• Assist with experiments on foundation models and jailbreaking.
• Communicate findings at meetings and conferences.

Skills

Foundation models

LLM jailbreaking

Safety alignment

Adversarial ML

Deep learning

Programming skills

Publishable research

Communication

Education

Master's degree

Tools

Python

Git

Job description

Department of Computer Science, Wolfson Building, Parks Road, Oxford, OX1 3QD

One Research Assistant (RA) Position - Generative AI, AI Safety, AI Security

One post tenable immediately, to conclude October 1st 2027 with the possibility of extension depending upon successful project review and project funding. Post offered at Grade 6 (£35,681- £39,424 per annum. This is inclusive of a pensionable Oxford University Weighting of £1,730 per year.).

The Department of Computer Science seeks to employ one Research Assistant (RA) to work within a research group, reporting to Prof Yarin Gal and Dr Lin Li. The postholder will be a member of the Oxford Applied and Theoretical Machine Learning (OATML) research group with responsibility for the provision of research support for projects relating to AI technical safety, security, reliability and robustness, as well as foundational research on frontier models like Large Language Models (LLMs) and multimodal foundation models. This includes topics such as safety alignment, adversarial training, jailbreaking, uncertainty quantification, and AI hallucination.

Candidates will be expected to have a Master’s degree (or be close to completion). They should have knowledge of foundation models (generative AI), LLM jailbreaking, safety alignment, adversarial machine learning, or deep learning, along with strong programming skills. Selection will also consider the ability to produce publishable research, communicate proposals and findings effectively, and represent the research group at meetings and conferences.

The closing date for applications is noon Friday 11th September 2026.

We are a Stonewall Top 100 Employer, Living Wage and Mindful Employer, holding an Athena Swan Bronze Award, HR excellence in Research and Race Equality Charter Bronze Award.

Our staff and students come from all over the world and we proudly promote a friendly and inclusive culture. Diversity is positively encouraged, through diversity groups and champions, for example http://www.cs.ox.ac.uk/aboutus/women-cs-oxford/index.html , as well as a number of family-friendly policies, such as the right to apply for flexible working and support for staff returning from periods of extended absence, for example shared parental leave.

Demonstrating a commitment to provide equality of opportunity. We would particularly welcome applications from women and black and minority ethnic applicants who are currently under-represented within the Computer Science Department. All applicants will be judged on merit, according to the selection criteria.

Salary (£) : £35,681- £39,424 per annum. This is inclusive of a pensionable Oxford University Weighting of £1,730 per year.