About the role
This is a hands-on security engineering role for people who are deep in cybersecurity and serious about AI. You will secure the AI systems being built — AI-enabled applications, models, agents, and the platforms beneath them, across their full lifecycle — acting as a trusted advisor who helps define and evolve the firm's AI security standards, patterns, and guardrails.
Responsibilities
•Act as security design authority for AI systems, leading threat modelling, architecture review, and risk assessment for agentic applications, the model gateway, Accio, Nexus, and any novel or high-risk AI initiative, applying STRIDE, PASTA, MITRE ATT&CK, and MITRE ATLAS as appropriate.
•Define and evolve AI security standards, guardrails, governance controls, and secure-by-design patterns aligned with enterprise requirements and the firm's risk appetite — co-designed with the Principal AI Architect as reusable, implementable guardrails, and implemented as code and secure defaults by AI Engineering and AI Platforms, working with the AI Governance Implementation Lead, who owns how they land on the platform.
•Design identity, entitlement, and secrets patterns for non-human identities — agents, tools, MCP servers, connectors, and service principals — with the Senior AI Platform Engineer and enterprise IAM, covering scoped permissions, credential lifetime, rotation, and least privilege across multi-hop requests.
•Set the trust boundaries and data-egress controls for the AI estate, including what may reach external model providers, and work with data protection owners on classification, DLP enforcement, privacy, and data governance obligations.
•Run adversarial testing and AI red teaming against models, prompts, agents, and tool chains, covering prompt injection and indirect injection, model manipulation and hijacking, excessive agency, function-call abuse, data leakage from LLM outputs, and privilege escalation between agents.
•Build detections, security analytics, and telemetry for AI-specific abuse — anomalous tool invocation, credential misuse by agents, unusual data access, and exfiltration through model responses — and integrate them into the firm's monitoring estate.
•Support security incident response for AI systems: triage, containment, forensics across prompts, tool calls, and agent decisions, and root cause, feeding each lesson back into platform defaults and evaluation suites.
•Own security testing in the AI delivery lifecycle, including static analysis, dependency and container scanning, secrets detection, and security gates in CI/CD, so issues surface before release.
•Co-own the risk-based security gate for onboarding new AI products, model providers, versions, and platform features with the Senior AI Platform Engineer and the AI Governance Implementation Lead, conducting security due diligence and risk assessment of AI vendors, platforms, and models — provenance, open-source components, tenancy and data-use terms, security advisories — and testing platform updates before rollout.
•Decide with the Senior AI Platform Engineer and the Principal AI Architect which Copilot features are released and to whom, withholding capability until the required controls are evidenced; review the solutions Forward Deployed Engineering builds and the platforms built with Percepta so neither reaches production without a security position; and set the guardrails for citizen developers and Copilot Studio makers with AI Enablement.
•Support Risk and Internal Audit with security evidence, exercise Infosec's security-control approval and risk-acceptance position for AI, and escalate where residual risk exceeds appetite.
•Identify and deliver opportunities to apply AI and automation across security operations, engineering, assurance, and governance, building automation with code, APIs, scripting, orchestration platforms, or low-code technologies to automate response workflows, enrich incident data, assist with triage, and drive risk-based vulnerability management.
•Define and report the KPIs, KRIs, dashboards, and reporting that demonstrate risk reduction, control effectiveness, and operational improvement.
•Mentor security engineers on AI security and build enough AI literacy across Infosec that this role is not a single point of knowledge.
Requirements
•Strong cybersecurity experience across security engineering, application security, product security, cloud security, or security architecture, with a hands-on engineering background, a track record of protections that reached production, and a solid grasp of security engineering fundamentals — common attack vectors, defence techniques, and threat modelling.
•Hands-on experience assessing and securing GenAI, LLM, machine learning, agentic AI, and AI-enabled solutions throughout their lifecycle.
•Proven ability to lead threat modelling, architecture reviews, and risk assessments for complex technology platforms and services.
•Strong understanding of AI-specific threats, threat modelling methodologies, adversary frameworks, and risk assessment approaches, including prompt injection, model manipulation, excessive agency, STRIDE, PASTA, MITRE ATT&CK, MITRE ATLAS, and equivalent industry practices.
•Experience defining and evolving AI security standards, guardrails, governance controls, and secure-by-design patterns aligned with enterprise requirements and risk appetite.
•Experience securing AI agents, MCP integrations, permissions, non-human identities, autonomous workflows, and AI platform integrations.
•Cloud security depth, ideally Azure — identity and access management, service principals and workload identity, secrets management, RBAC, network controls, and logging — and experience securing application delivery, including secure SDLC, CI/CD controls, and code and dependency scanning.
•Practical experience with AI and LLM systems — prompt engineering, retrieval-augmented generation, function calling, agent-based tools — and proven ability to build and deploy automation using code, APIs, scripting, orchestration platforms, or low-code technologies such as Python, workflow engines, or SOAR, integrating security logs, AI models, and platform components into cohesive pipelines.
•Metrics-driven mindset, with experience defining KPIs, KRIs, dashboards, and reporting to demonstrate risk reduction, control effectiveness, and operational improvement.
•Strong stakeholder engagement and influencing skills, with the ability to translate technical risk into business impact, pragmatic controls, and informed risk decisions — and the independence to hold a security position under delivery pressure.
Nice to have
•Familiarity with AI security and governance frameworks including NIST AI RMF, the OWASP Top 10 for LLM applications, MITRE ATLAS, ISO/IEC 42001, and the security provisions of the EU AI Act.
•AI red teaming, adversarial testing, adversarial machine learning, model validation, or offensive security assessments applied to models and tool chains.
•Experience securing enterprise AI platforms, model gateways, AI development environments, and AI engineering ecosystems.
•Knowledge of AI security posture management, runtime protection, model monitoring, and AI governance tooling.
•Knowledge of identity security, including IAM, PAM, identity governance, privileged access management, non-human identities, and workload identities.
•Experience applying AI and automation to vulnerability management, detection engineering, threat detection, or security operations at scale, including risk-based threat prioritisation.
•Knowledge of security analytics, monitoring, and detection capabilities for AI systems and supporting infrastructure.
•Understanding of privacy, data governance, regulatory, and responsible AI considerations, including Microsoft Purview, DLP policy design, or data classification across a Microsoft 365 estate.
Benefits
•Hybrid working and reasonable accommodations
•Generous Holiday policies
•Excellent Health and Wellbeing benefits including corporate membership to Wellhub
•Paid volunteer time to step away from your desk and into the community
•Support to grow through professional development courses, tuition/qualification reimbursement and more
•Maternal/paternal leave benefits and family services
•All employee events including networking opportunities and social activities
•Lunch allowance for use within the subsidized onsite canteen
