Agentic AI Security Engineer: Red Team & Governance

ClearRoute Limited; Greater London; On-site; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Profit sharing

Private healthcare

Home office budget

Flexible hybrid working

Learning budget (Udemy)

Job summary

ClearRoute Limited seeks an experienced security engineer to lead agentic AI testing across multiple accounts, designing governance and reusable testing approaches. You will test prompts, evaluate risk, and mentor the team to automate the strategy across engagements.

You will shape the test strategy for agentic security, collaborate with delivery teams, and focus on governance as the practice matures, including training others.

Qualifications

• Hands-on red-teaming or adversarial testing of LLM or agentic AI systems.
• Understanding of how to test non-deterministic systems and mitigate hallucinations.
• Familiarity with agentic AI risk frameworks and taxonomies (OWASP, MITRE ATLAS).
• Experience with OWASP Top 10 for LLM Applications (prompt injection, leakage).
• Ability to translate risks into organisational controls within governance.
• Able to operate across accounts and teams and build reusable test strategies.
• Strong communication to both technical and non-technical stakeholders.
• Willingness to implement tests hands-on and later mentor others.

Responsibilities

• Design and run red-team exercises against AI agents and agentic workflows.
• Build repeatable evaluation methods for non-deterministic outputs.
• Define and manage detection and mitigation of hallucinations in outputs.
• Own agentic AI risk identification and governance across an account.
• Map findings to external frameworks (OWASP, NIST, MITRE ATLAS).
• Distinguish controls for internal vs client-facing views of agent behavior.
• Define rollback and incident-response procedures for agentic systems.
• Track regulatory expectations (EU AI Act) and translate to practical requirements.
• Train and upskill security engineers to implement the strategy across teams.

Skills

Red-teaming

LLM testing

Prompt injection

Non-deterministic testing

AI risk frameworks

Threat modelling

Stakeholder comms

Mentoring

Agentic security testing

Tools

Terraform

CI/CD

Security tooling

Job description

ClearRoute Limited seeks an experienced security engineer to lead agentic AI testing across multiple accounts, designing governance and reusable testing approaches. You will test prompts, evaluate risk, and mentor the team to automate the strategy across engagements.

You will shape the test strategy for agentic security, collaborate with delivery teams, and focus on governance as the practice matures, including training others.