"AI Security Research Role"

Assurance and verification offerings for AI are fragmented and target specific areas of AI lifecycle (e.g. model assurance or prompt injections) without offering a unified view of the security of an AI System. The role involves performing research to create a configurable AI agentic framework that 1) integrates with the full security lifecycle of a system whilst 2) providing innovative verification and assurance options. Specifically, the role will involve investigating:

1. Excessive Agency and discovery of data and other misconfigured attack vectors an AI system can exploit.
2. Misuse, by analysing access and system logs using anomaly detection.
3. Sensitive Data Exposure, by helping identify memorised data in finetuning settings, misconfigured access control, or leaks in RAG settings.
4. Supply chain by integrating existing MLSecOps, DevSecops and advance techniques for 3rd party model assessment as part of provenance.

About the person:

To be considered for interview, applicants must demonstrate that they meet the essential criteria for the post, which includes:

• Have or be about to obtain a PhD in computer science, engineering, mathematics or physical sciences area.
• Recent high quality research experience in machine learning/AI or cybersecurity, or both, as evidenced by a strong track record of publications in leading journals and conferences in relevant areas.
• Software programming skills.

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 on our website.

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.

What we offer:

Beyond a competitive salary, the University offers an attractive benefits package including a holiday entitlement of up to 8.4 weeks a year, pension schemes and development opportunities. We support staff wellbeing with flexible working options, work-life balance initiatives and support for physical and mental health. Queen's University is committed to promoting equality of opportunity to all. We subscribe to Equality Charter Marks such as the Diversity Charter Mark NI and Athena Swan and have established staff networks such as iRise (Black, Asian, Minority Ethnic and International Staff Network) and PRISM (LGBTQ+) which help us progress equality.

For further information on our commitment to Equality, Diversity and Inclusion, please visit our website.

If you are an international applicant and don't already hold a visa that permits you to take up the role you are applying for, please use the information provided on our website to self-assess whether the University is likely to be able to support a visa application.