AI Security Engineer (Agentic Systems)

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

Benefits offered by this job

Profit sharing

Private healthcare

Home office budget

Learning budget

Job summary

ClearRoute Limited seeks a senior security tester focused on agentic AI and governance. You will test AI use cases across accounts, identifying risk, setting testing strategy and building defensible controls.

The role starts hands-on and grows into governance, mentoring other security engineers to broaden capability across the firm. You will work with delivery teams, map findings to recognized frameworks, and help embed testing into workflows while maintaining a strong client-facing posture and

Qualifications

• Hands-on experience red-teaming or adversarially testing LLM or agentic AI systems.
• Practical understanding of testing non-deterministic systems and mitigating hallucinations.
• Knowledge of agentic-AI risk frameworks and taxonomies (OWASP, MITRE ATLAS).
• Experience with OWASP Top 10 for LLM Applications and prompt injection.
• Experience applying AI governance frameworks (e.g., NIST AI RMF) to organizational controls.
• Ability to operate across accounts and teams with reusable test strategy and tooling.
• Threat modelling and security review experience.
• Strong communication to explain AI risk to tech and non-tech stakeholders.
• Hands-on testing first, then mentoring others in agentic testing.

Responsibilities

• Design and run red-team exercises against AI agents and agentic workflows.
• Build repeatable evaluation approaches for non-deterministic systems.
• Define and own an approach for detecting and mitigating hallucinations in outputs.
• Own agentic AI risk identification and governance across an account.
• Map findings to frameworks like OWASP, NIST AI RMF, MITRE ATLAS.
• Distinguish and design controls for internal vs client-facing views.
• Define rollback and incident-response procedures for agentic systems.
• Track regulatory expectations (EU AI Act) and translate to practical tests and governance.
• Work across delivery teams, advising on tooling and embedding into workflows.
• Train security engineers to implement and automate testing for wider adoption.

Skills

Red teaming

Adversarial testing

LLM testing

Non-deterministic systems

Threat modelling

AI governance

OWASP ATLAS

NIST AI RMF

MITRE ATLAS

Cross-team collaboration

Communication skills

Tools

Azure

Terraform

CI/CD pipelines

Job description

ClearRoute is an engineering consultancy bridging Quality Engineering, Cloud Platforms and Developer Experience. We help enterprises reliably bring high-impact digital products to market faster, cheaper, and safer, working with technology leaders facing complex business challenges.

We take as much pride in our people, culture and work-life balance as we do in making better software. We’re not just making better software. We’re making the making of software better. Collaborative, entrepreneurial and dedicated to problem solving, we bring the step change our customer need to sustain innovation. Our values challenge us to do the best we can for ClearRoute, our customers and most importantly our team. This is an opportunity for you to build the organisation from the ground up, use your voice to drive change and help transform organisations and problem domains.

Role

This role sits apart from our traditional cloud security engineering positions: it is centred on AI and agentic systems rather than infrastructure alone. You will test and secure AI use cases across an account, not one application or user set, building a broad, first‑hand picture of how ClearRoute should approach testing, risk and governance for agentic AI.

You will work across teams rather than within one delivery stream, owning the question of what \"good\" looks like for agentic security testing across the account, and helping ClearRoute build a repeatable, defensible approach that other engagements can adopt.

The role is deliberately hands‑on in its first phase: you will implement and run the testing yourself, so you understand the detail before asking anyone else to follow it. As that practice matures, the role shifts toward governance across the account, training and upskilling existing security engineers to implement and automate the strategy themselves, so agentic security testing becomes something the wider team can run, not something that depends on one person.

Key Responsibilities

Agentic Red Teaming & Adversarial Testing:

• Design and run red‑team exercises against AI agents and agentic workflows, probing for prompt injection (direct and indirect), tool‑call and argument manipulation, agent hijacking, memory/context poisoning, and privilege or credential escalation.
• Build repeatable evaluation approaches for non‑deterministic systems, including how to test, measure and report against outputs that vary run to run.
• Define and own an approach for detecting, measuring and mitigating hallucinations in agent and LLM outputs, distinct from traditional functional‑testing methods.

Agentic Governance & Risk:

• Own agentic AI risk identification and governance across an account, not one application: build the risk view, the test strategy and the tooling recommendations that other teams can reuse.
• Map findings and controls to recognised external frameworks (for example OWASP's agent‑specific risk taxonomy, NIST's AI Risk Management Framework Govern function, and MITRE ATLAS) so ClearRoute's approach is defensible and auditable,
• Distinguish and design controls for internal versus external (client‑facing) views of agent behaviour, including how outputs are reviewed, sanitised or gated before release.
• Define rollback and incident‑response procedures for agentic systems, so a compromised or misbehaving agent can be safely withdrawn or reverted.
• Track emerging regulatory expectations relevant to AI testing (for example EU AI Act provisions on adversarial and robustness testing) and translate them into practical test and governance requirements.

Cross‑Team & Organisational Scope:

• Work across delivery teams and accounts, acting as the connective view on agentic security testing rather than being embedded in one application or team
• Recommend and help select tooling for agentic security testing and monitoring, and advise delivery teams on how to embed it into their workflow
• Represent ClearRoute's agentic security posture with internal stakeholders and, where relevant, clients
• Train and upskill existing security engineers over time so agentic testing and automation becomes a capability the wider team owns, not one specialist

Required Skills & Experience

Must Have:

• Hands‑on experience red‑teaming or adversarially testing LLM or agentic AI systems, including prompt injection, jailbreaking and tool‑misuse scenarios
• Practical understanding of how to test non‑deterministic systems and how to detect, quantify and mitigate hallucination
• Working knowledge of agentic‑AI‑specific risk frameworks and taxonomies, such as OWASP's agent risk categories and MITRE ATLAS
• Experience with the OWASP Top 10 for LLM Applications, including prompt injection and system‑prompt‑leakage risk categories
• Experience designing or applying an AI governance framework (for example NIST's AI Risk Management Framework) to translate identified risks into organisational controls
• Ability to operate across accounts and teams, building test strategy and tooling recommendations that generalise beyond one application
• Threat modelling and security review experience
• Strong communication skills, able to explain agentic AI risk clearly to technical and non‑technical stakeholders, including on what should and shouldn't be released to clients
• Comfortable being hands‑on first — implementing and running agentic security tests directly — then mentoring and training other security engineers to take the practice on themselves

Nice to Have:

• Familiarity with agent‑hijacking or agent‑specific evaluation tooling (for example open‑source agent‑security benchmarks)
• Awareness of emerging AI regulation relevant to security testing, such as the EU AI Act's adversarial and robustness‑testing requirements
• Experience with multi‑agent or agent‑mesh systems and the trust/authentication issues between agents
• Cloud security background (Azure preferred) and Terraform and CI/CD
• Experience in a regulated sector (for example financial services)

Working at ClearRoute

We have grown from six founders to 200+ people across five countries in three years, and what sets us apart isn't the pace, it's how we grow.

• Real flexibility, in practice. We trust you to perform at your best and still have a life outside of work, with genuine hybrid working, a home office budget, an open feedback culture where your voice shapes decisions, and time off when life needs it (birthday included).
• When ClearRoute wins, you win. We offer profit share so success is shared, meaningful recognition for great work, and benefits that look after you and your family, including private healthcare, competitive salary benchmarking, and a confidential employee assistance program covering counselling, mental health support, and financial wellbeing.
• A community you'll genuinely want to be part of. Interest based communities like running and book clubs, WomenInTech group, monthly socials, and cross regional events bring people together across the company. An inclusive, collaborative culture where you don't need to conform to succeed, where people support one another and feel comfortable being themselves.
• Where meaningful work meets real growth. You will tackle complex, real world problems at the forefront of platform engineering, AI, security, and scalable systems. Your growth is supported by learning budgets, Udemy access, a clear career framework, internal mobility, and thought leadership opportunities that take your impact beyond ClearRoute.

At ClearRoute, we believe diverse perspectives lead to better outcomes, and inclusion creates the conditions for everyone to thrive. We are proud to have built a family friendly working environment and have many employees who have caring responsibilities alongside work. We welcome applications from people who require flexibility and will be happy to discuss needs on an individual basis.

We are committed to fostering a culture where all team members feel respected, supported, and empowered to do their best work. We celebrate individuality and our differences and understand that some differences may mean that you require changes made to the interview process. We are happy to cater to your needs to make the interview accessible, if this is something you require please let us know by emailing us at [e-mail]