Agentic AI Security Engineer

ClearRoute Limited; England; Hybrid; GBP 90,000 - 120,000; Full time

Benefits offered by this job

Profit sharing

Private healthcare

Home office budget

Hybrid working

Job summary

ClearRoute Limited is seeking an experienced security engineer to lead agentic AI testing and governance across multiple accounts. You will hands-on test AI agents, design red-team exercises, and define risk-based controls.

As the role matures, you’ll mentor security engineers, develop repeatable testing strategies, and map findings to OWASP, MITRE ATLAS, and NIST frameworks while collaborating with cross-functional teams.

Qualifications

• Hands-on red-teaming or adversarial testing of LLM or agentic AI systems including prompt injection and tool-misuse scenarios.
• Practical understanding of testing non-deterministic systems and how to detect, quantify and mitigate hallucination.
• Familiarity with agentic-AI risk frameworks and taxonomies (OWASP agent risk, MITRE ATLAS).
• Experience with OWASP Top 10 for LLM Applications, including prompt injection and system-prompt-leakage.
• Ability to translate risks into organisational controls using AI governance frameworks (e.g., NIST).
• Ability to operate across accounts and teams, building generalisable test strategy and tooling.
• Threat modelling and security review experience.

Responsibilities

• Design and run red-team exercises against AI agents and agentic workflows, probing for prompt injection, tool-call and argument manipulation, agent hijacking and context poisoning.
• Build repeatable evaluation approaches for non-deterministic systems, including how to test and report outputs that vary run to run.
• Define and own an approach for detecting, measuring and mitigating hallucinations in agent and LLM outputs.
• Own agentic AI risk identification and governance across an account; map findings to external frameworks for defensibility.
• Train and upskill security engineers to implement and automate agentic testing and governance across teams.

Skills

Red-team testing

LLM testing

Prompt injection

Non-deterministic systems

AI risk frameworks

Threat modelling

Cross-account collaboration

Communication skills

Tools

OWASP

MITRE ATLAS

NIST AI RMF

Azure security

Terraform / CI/CD

Job description

ClearRoute Limited is seeking an experienced security engineer to lead agentic AI testing and governance across multiple accounts. You will hands-on test AI agents, design red-team exercises, and define risk-based controls.

As the role matures, you’ll mentor security engineers, develop repeatable testing strategies, and map findings to OWASP, MITRE ATLAS, and NIST frameworks while collaborating with cross-functional teams.