Research Assistant in Agentic AI Security

About the Role

Security Copilots, AI coding assistants and automated code-review agents are being adopted rapidly across industry and government, introducing new attack surfaces that can propagate directly into the supply chain. The post-holder will help the project team discover, characterise and mitigate these vulnerabilities. Typical duties include implementing proof-of-concept attacks and defences against coding and review agents, curating vulnerable-code datasets, and contributing to papers, demos and industry outreach. The post is ideal for an MSc graduate (or exceptional BSc Hons) who wants to gain deep, publishable experience before a PhD or industrial R&D care er.

About the Person

The successful candidate must have, and your application should clearly demonstrate that you meet the following essential criteria:

• Hold a 2:1 Degree or above BSc in Computer Science, Cyber-security, AI or related. MSc is desirable for this position.
• Have significant Python programming experience
• Have familiarity with at least one LLM framework or API (Hugging Face, llama.cpp)
• Have solid software-engineering and version-control (Git) practice

To be successful at shortlisting stage, please ensure you clearly evidence in your application how you meet the essential and, where applicable, desirable criteria listed in the Candidate Information.

Fixed-term contract (12 months or until 30 September 2027, whichever is soonest). Fixed term contract posts are available for the stated period in the first instance but in particular circumstances may be renewed or made permanent subject to availability of funding.