AI Security Engineer

Overview

In this hands-on security engineering role, you secure AI-enabled systems across their lifecycle, partnering with AI Technology and the broader security function. You will define and evolve AI security standards, patterns, and guardrails to scale enterprise AI use while maintaining strong risk controls. You act as a design authority for AI systems, balancing security with velocity to deliver business value. You join a firm undergoing a central AI transformation with a focus on practical, built-in security rather than added-on processes.

Pay / Benefits

• Hybrid working
• Generous Holiday policies
• Health and wellbeing benefits
• Volunteer time
• Professional development and tuition reimbursement
• Parental leave

Responsibilities

• Act as security design authority for AI systems, leading threat modelling, architecture reviews, and risk assessments for agentic apps, model gateway, Accio, Nexus, and other high-risk initiatives.
• Define and evolve AI security standards, guardrails, governance controls, and secure-by-design patterns, co-designing reusable guardrails with the Principal AI Architect and implementing them as code by AI Engineering and AI Platforms.
• Design identity, entitlement, and secrets patterns for non-human identities across multi-hop requests, collaborating with enterprise IAM and the Senior AI Platform Engineer.
• Set trust boundaries and data-egress controls for AI estate, coordinating with data protection owners on classification, DLP, privacy, and data governance.
• Run adversarial testing and AI red teaming, build detections and telemetry for AI-specific abuse, and integrate them into the monitoring estate.
• Own security testing in the AI delivery lifecycle, including static analysis, dependency and container scanning, secrets detection, and CI/CD security gates.
• Co-own risk-based security gate for onboarding AI products and models, performing security due diligence and risk assessment of vendors and platforms, and testing updates before rollout.
• Identify and deliver opportunities to apply AI and automation across security ops, engineering, assurance, and governance, building automated response workflows and risk-based vulnerability management.
• Mentor security engineers on AI security and promote AI literacy across Infosec to avoid single points of knowledge.

Key requirements

• Strong cybersecurity experience across security engineering, application security, product security, cloud security, or security architecture with hands-on engineering background and production protections.
• Hands-on experience assessing and securing GenAI, LLM, ML, agentic AI throughout their lifecycle.
• Proven ability to lead threat modelling, architecture reviews, and risk assessments for complex platforms.
• Strong understanding of AI-specific threats and frameworks (STRIDE, PASTA, MITRE ATT&CK, MITRE ATLAS).
• Experience defining and evolving AI security standards and secure-by-design patterns.
• Experience securing AI agents, MCP integrations, permissions, non-human identities, autonomous workflows, and AI platform integrations.
• Cloud security depth (preferably Azure) including IAM, secrets management, RBAC, networking, logging; secure SDLC and CI/CD controls.
• Practical experience with AI/LLM systems and building automation via code, APIs, scripting, orchestration, or low-code tech; Python or similar.
• Metrics-driven with KPIs/KRIs; strong stakeholder engagement and ability to translate risk into business impact.

• Stakeholder engagement and influencing skills
• Pragmatic risk decision making under delivery pressure
• Independence to push back when necessary
• Azure cloud security (IAM, workload identity, secrets management, RBAC)
• Security in CI/CD, code and dependency scanning
• Threat modelling methodologies (STRIDE, PASTA) and MITRE ATT&CK/ATLAS

…