Research Engineer, Agentic Critical Systems Cyber Security

The Alan Turing Institute; Greater London; On-site; GBP 46,000 - 51,000; Full time

Benefits offered by this job

Flexible working

Family friendly policies

Job summary

The Alan Turing Institute is seeking a candidate to work in the Defence & National Security team, focusing on LLM-driven agentic systems for autonomous hardening of legacy OT/ICS in Critical National Infrastructure. You will design, build and evaluate AI pipelines, develop virtualised training environments, and contribute to published outputs.

Requirements include a master's degree or equivalent, experience with LLM APIs, and knowledge of network security.

Qualifications

• Experience integrating with LLM APIs and building agentic/ tool-calling pipelines.
• Master’s degree or equivalent experience in a relevant field.
• Understanding network security principles (defensive and offensive).
• Evidence of published outputs in related research.

Responsibilities

• Design, build and evaluate agentic AI systems for CNI resilience.
• Develop virtualised environments with legacy OT/ICS hosts.
• Plan and run AI-based CNI red-blue competitions with robust eval protocols.
• Publish outputs and communicate results effectively.

Skills

LLM API integration

Agentic systems

Tool-calling pipelines

Multi-step reasoning

Publications track record

Defensive security

Offensive security

Education

Master's degree or equivalent

Tools

LangGraph

MCP

Job description

Building on the successes of AI for Cyber Defence (AICD) Research Centre, the Defence & National Security (D&NS) team at the Alan Turing Institute is developing an ambitious programme of research to deliver a fundamental shift in Critical National Infrastructure (CNI) cyber-resilience using AI. The focus of this new programme is the cyber resilience of CNI, including legacy operational technology (OT) and end-of-life operating systems; both of which underpin critical sectors from energy and water to data operations, but that cannot be patched, upgraded, or modified without risking operational disruption or invalidating safety certification. This role will sit within the D&NS team and focus on advancing resilience of CNI by designing, building, and evaluating LLM-driven agentic systems for the autonomous hardening of legacy operational technology and industrial control systems.

ABOUT YOU

The ideal candidate will have experience integrating with LLM APIs and building agentic or tool-calling pipelines to implement multi-step reasoning workflows (e.g. MCP, LangGraph). You’ll use your knowledge from a master’s degree (or equivalent experience), utilising a range of methodologies to tackle problems set by the partner. You’ll need a understanding network security principles e.g. defensive and offensive security, this will be teamed with the work you do when you plan and run AI-based CNI red-blue teaming competitions. All of your experience will be needed when you develop realistic virtualised environments with legacy OT/ICS hosts, having experience of this is key to move the project forward.

Publishing our outputs is key to the role, so you would have a track record of first authorised or contributed heavily to previous publications so you can hit the ground running – this is also where your excellent verbal and written communication skills come in.

HOW YOU WILL MAKE AN IMPACT

• Collaboratively design, build and maintain agentic, AI systems and evaluation suites that support CNI cyber resilience and legacy software hardening against known vulnerabilities.
• Develop virtualisation based digital twin environments and implement techniques for assuring operational continuity in the context of CNI.
• Develop CNl-relevant scenarios with clear threat models, operational continuity criteria, and defensible assumptions; document limitations and known failure modes explicitly.
• Run large-scale evaluations on HPC and cloud platforms, improving performance and reliability through batching/parallelisation, resource-aware execution, and systematic debugging of non-determinism and environment drift.
• Play a role in planning and running AI-based CNI red-blue teaming competitions, ensuring robust environment design and evaluation protocols are in place.

Please see our portal for a full breakdown of the role.

Closing date for applications: SUNDAY 06 SEPTEMBER 2026 at 23:59 (London, UK BST)

Term and Conditions

This full-time post is offered on a 12-month fixed term basis. The annual salary is £45,505 - £51,241 plus excellent benefits, including flexible working and family friendly policies, Employee-only benefits guide | The Alan Turing Institute

Eligibility for Security Check (SC) clearance is a requirement for this role.

The Alan Turing Institute is based at the British Library, in the heart of London’s Knowledge Quarter. We expect staff to come to our office at least 4 days per month. Some roles may require more days in the office; the hiring manager will be able to confirm this during the interview.

Equality, Diversity and Inclusion

The Alan Turing Institute is committed to creating an environment where diversity is valued and everyone is treated fairly. We value diversity of background, experience, and perspective, and are proud to be an inclusive employer. We warmly encourage applications from all backgrounds, particularly from groups currently under-represented in our sector. If you feel passionate about this role but don’t meet every single requirement, please apply - we recognise that great candidates may bring strengths beyond the criteria listed