Research Associate / Senior Research Associate / Research Fellow in Security Assurance for Agentic

Overview

The Smart Internet Lab at the University of Bristol invites applications for a Research Associate, Senior Research Associate, or Research Fellow in Security Assurance for Agentic AI. This position is part of the newly funded AURA project, which introduces autonomous AI-driven network management across critical network infrastructure. The role focuses on addressing security challenges within AI-native Future Networks architectures to ensure the AI management layer remains trustworthy, secure, and resilient. The successful candidate will conduct novel academic and high Technology Readiness Level Agentic AI security assurance research, which involves characterizing threat landscapes, conducting adversarial testing, developing runtime assurance mechanisms, and enforcing zero-trust principles on the autonomous AI layer.

Who can apply

Candidates must hold a PhD, be near completion of a PhD, or possess equivalent research and development experience in computer science, computer engineering, networks, or communications. Applicants need an in-depth understanding of fundamental cybersecurity concepts, threats, vulnerabilities, and AI applications in network security, along with demonstrated experience in Agentic AI security in 5G and Beyond networks. A working knowledge of telecom standards and specifications such as O-RAN, 3GPP, and ETSI is required. Candidates must also have programming experience, preferably using Python within a Linux or Unix-based research or development environment, and experience conducting experimental research using systematic approaches. Applicants for higher grades, such as Senior Research Associate or Research Fellow, must demonstrate substantial postdoctoral or equivalent research experience, independent research leadership, and specialist knowledge in areas including artificial intelligence and machine learning security, agentic AI, zero-trust frameworks, and cloud-native observability tools.

What you get

The position offers a salary ranging from £40,704 to £59,390 per annum depending on experience. The employment is a full-time, permanent contract with a work pattern of 35 hours per week, supported by fixed funding until 29 February 2028.

Requirements

The role requires identifying and documenting the threat landscape across data ingestion, intent interfaces, and execution layers of Agentic AI systems. Responsibilities include simulating and demonstrating agent misuse and multi-agent coordination attack scenarios, designing and implementing intent-to-policy mapping, and developing a runtime decision validation engine. The appointee will implement dynamic trust scoring mechanisms, develop automated mitigation strategies such as rollbacks and agent isolation, publish research findings in high-impact journals, present at leading conferences, and evaluate research experimentally using the project partner platform and the University of Bristol JOINER national open-networks experimentation infrastructure.

Key dates

The application deadline is 5 November 2026 at 23:59 UK time.