Lead AI Security Engineer – Agentic Platform

Ernst & Young Oman; Carson City (NV); Remote; USD 150,000 - 210,000; Full time

Job summary

EY is seeking an AI Security Engineer to own the security posture of EY's Agentic AI platform end to end. The role spans silicon-level attestation through sandboxed execution and audit-grade evidence, emphasizing cloud-native security and AI threat modeling.

This is a senior position ideal for a principal security engineer who can write threat models, perform red-teaming, define policy-as-code, and defend the platform to CISOs and regulators.

Qualifications

• Principal security engineer with depth in cloud-native and platform security, moving into AI and agentic threat models.
• Ability to write threat models, conduct red-teaming, define policy-as-code, and defend engineering to CISOs or regulators.

Responsibilities

• Own the platform threat model covering agent autonomy, tool invocation, delegated authority, and multi-tenant deployments.
• Define the security engineering and control set for infrastructure, Kubernetes, identity, secrets, and telemetry.
• Set the secure-by-default contract so platform capabilities arrive hardened with correct controls.
• Own defense against agentic threat classes including prompt injection, jailbreaks, and abuse of tools.
• Help define the agent authority model with scope, delegation-depth limits, and non-escalation invariants.
• Own the sandboxing security standard for agent-generated code execution and escape-test suites.
• Secure the model and knowledge supply chain including provenance and integrity.

Skills

AI security

Threat modeling

Cloud security

Kubernetes security

Red teaming

Tools

Kubernetes

Terraform

Job description

EY is seeking an AI Security Engineer to own the security posture of EY's Agentic AI platform end to end. The role spans silicon-level attestation through sandboxed execution and audit-grade evidence, emphasizing cloud-native security and AI threat modeling.

This is a senior position ideal for a principal security engineer who can write threat models, perform red-teaming, define policy-as-code, and defend the platform to CISOs and regulators.