Senior Research Associate - AI Agent Security; two

Overview

AI Agent Security & Safety — We are seeking candidates to join our AI security group at Lancaster University to contribute to this rapidly growing research field.

• Research how to defend AI agents from cyber attacks in the context of Shadow AI, the deployment and use of AI within an organisation without knowledge or approval from security teams.
• Collaborate with an expanding AI security lab and a large-scale GPU data center containing state-of-the-art foundation models.
• Work with industry researchers to tackle real-world problems, including direct collaboration with Mindgard ((Use the "Apply for this Job" box below).).
• Develop prototypes and software to disseminate research findings into industry, contributing to security and privacy of AI applications on the edge.

• PhD in Computer Science, with expertise in cybersecurity, Artificial Intelligence, or distributed systems.
• Direct experience in AI security, Adversarial Machine Learning, or workload anomaly detection is a bonus.
• Strong software development skills and experience creating prototypes to share findings with industry.

The Edge AI Hub () is a £10M EPSRC project dedicated to systematic understanding of cyber disturbances in edge AI. This project offers opportunities to work with an international team of researchers spanning multiple institutions in academia and industry as part of the flagship UKRI hub in AI. The School of Computing and Communications at Lancaster University holds notable rankings and ongoing investments in Security and Protection Science, underscoring the strategic importance of cybersecurity research at Lancaster.