Senior AI Security Engineer — Agentic Platform Defense

Ernst & Young Oman; Seattle (WA); On-site; USD 180,000 - 240,000; Full time

Job summary

Ernst & Young seeks an AI Security Engineer to own the security posture of EY's Agentic AI platform end to end, spanning silicon-level attestation to sandboxed execution.

The role demands depth in cloud-native security and AI threat models, with the ability to defend engineering outcomes to CISOs and regulators. This broad mandate suits a security leader comfortable across strategy and hands-on defense.

Qualifications

• Must be able to articulate and maintain a platform threat model covering agent autonomy, tool invocation, delegated authority, model/data supply chains, and multi-tenancy.
• Define security engineering and control sets for all platform layers including infrastructure, Kubernetes, identity and secrets, secure execution and telemetry.
• Set a secure-by-default contract with hardened capabilities and templates.
• Lead defense against agentic threat classes including prompt injection and jailbreak risks.

Responsibilities

• Own the platform threat model and keep it current through build phases.
• Define security controls for each platform layer (infrastructure, Kubernetes, identity, sandboxing, data, telemetry).
• Set the secure-by-default contract so platform capabilities ship hardened.
• Defend against agentic threat classes and ensure proper containment and auditing.
• Collaborate with architecture to define agent authority models and non-escalation invariants.
• Own sandboxing standards for code execution and isolation.
• Secure model and knowledge supply chain including provenance and integrity.
• Secure agent-to-agent and tool protocols with verification and authorization.
• Lead AI red teaming and adversarial testing to strengthen defenses.

Skills

Platform threat modeling

Cloud-native security

AI security / agentic threat models

Red teaming

Policy as code

Job description

Ernst & Young seeks an AI Security Engineer to own the security posture of EY's Agentic AI platform end to end, spanning silicon-level attestation to sandboxed execution.

The role demands depth in cloud-native security and AI threat models, with the ability to defend engineering outcomes to CISOs and regulators. This broad mandate suits a security leader comfortable across strategy and hands-on defense.