Lead Agentic AI Security Researcher for 5G & Zero-Trust

University of Bristol; West of England; On-site; GBP 41,000 - 59,000; Full time

Job summary

University of Bristol’s Smart Internet Lab seeks an outstanding researcher to join the AURA project, focusing on security for AI-native networks. You will explore threat landscapes, implement runtime validation, and enforce zero-trust principles on autonomous AI layers within private 5G networks.

The role requires a PhD (or near completion) in computer science, networking or security, with Python/Linux expertise and experience in experimental research.

Qualifications

• Candidates hold a PhD or near completion in a related field and have research experience in computer science, networks or security.
• Strong understanding of cybersecurity threats, vulnerabilities and AI in network security.
• Experience with Agentic AI security in 5G/Beyond networks and knowledge of telecom standards.
• Programming experience, preferably Python, in a Linux/Unix research environment.
• Experience conducting experimental research using systematic approaches.

Responsibilities

• Identify and document threat landscapes across data ingestion, intent interface and execution layers of the Agentic AI system.
• Simulate agent misuse and multi-agent attacks on a live partner platform to map attack surfaces.
• Design intent-to-policy mapping translating agent intent into verifiable constraints.
• Develop a runtime decision validation engine against cross-layer security models.
• Implement dynamic trust scoring and automated mitigation strategies for compromised agents.
• Publish findings in high-impact journals and present at top security conferences.
• Evaluate research using partner platforms and university testing infrastructure.

Skills

Cybersecurity concepts

Agentic AI security in 5G

Python programming

Linux/Unix

Experimental research methods

Telecom standards knowledge

Education

PhD or equivalent research experience

Job description

University of Bristol’s Smart Internet Lab seeks an outstanding researcher to join the AURA project, focusing on security for AI-native networks. You will explore threat landscapes, implement runtime validation, and enforce zero-trust principles on autonomous AI layers within private 5G networks.

The role requires a PhD (or near completion) in computer science, networking or security, with Python/Linux expertise and experience in experimental research.