Lead AI Cyber Security Engineer

As Lead AI Cyber Security Engineer, you will own the end-to-end security posture of the AI layer. You’ll engineer guardrails, red-team live agents, design zero-trust controls, and defend our architecture directly to the client’s CISO and regional regulators (CBUAE).

Key Responsibilities

• AI & LLM Security: Engineer prompt injection defenses, output schema validation, jailbreak resistance, and deterministic guardrails around tool execution.
• Red Teaming & Threat Modelling: Lead adversarial testing (indirect prompt injection, tool abuse, context exfiltration) and automate attack suites into CI/CD pipelines.
• Zero-Trust Architecture: Design secure AI-to-API communication (mTLS, OAuth 2.0/OIDC) to ensure AI reasoning can never touch core ledgers without explicit policy checks.
• Compliance & Auditability: Architect Model Risk Management (MRM) controls, CBUAE compliance mechanisms, and tamper-evident audit trails for every agent action.
• DevSecOps & Leadership: Enforce security gates in CI/CD, conduct pod-level design reviews, and present security postures to executive client stakeholders.

Requirements

• 8+ years of hands-on Security Engineering experience (Zero-Trust, API security, DevSecOps, Cloud/K8s security).
• 2+ years securing LLM or agentic systems in production.
• Hands-on Red Teaming: Strong practical experience with OWASP Top 10 for LLMs, jailbreaks, and guardrail engineering.
• Fintech / Banking Background: Experience with PCI-DSS, transactional logging, and banking regulatory frameworks (CBUAE/DFSA preferred).
• Technical Degree: Computer Science, Cyber Security, or equivalent. Relevant certs (CISSP, CCSP, OSCP) or published AI security research are a plus.

Work Conditions
This job can be filled in Dubai/UAE.