Senior AI Security Engineer: Agentic Platform Defense

Ernst & Young Oman; Rogers (AR); Remote; USD 120,000 - 180,000; 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. This role requires deep cloud-native security experience and expertise in AI threat models to defend against complex, multi-tenant deployments.

You will lead threat modeling, red teaming, and policy-as-code efforts, and work with architects to define agent Authority and sandboxing standards for secure execution.

Qualifications

• Experience shaping platform threat models for cloud-native systems.
• Depth in AI/agentic threat models and secure software delivery.
• Ability to write threat models and defend engineering to CISOs/regulators.

Responsibilities

• Own the platform threat model across deployment targets from cloud to air-gapped.
• Define security engineering and control set for each platform layer.
• Set the secure-by-default contract with agent templates and network policy.
• Defend against agentic threat classes including prompt injection.
• Lead AI red teaming and adversarial testing.
• Define agent authority model with delegation-depth limits.
• Own sandboxing security standard for code execution.
• Secure the model and knowledge supply chain.
• Secure agent-to-agent and tool protocols.

Skills

Threat modeling

AI security

Red Teaming

Cloud-native security

Policy as code

Tools

Kubernetes

Helm

Job description

EY is seeking an AI Security Engineer to own the security posture of EY's Agentic AI platform end to end. This role requires deep cloud-native security experience and expertise in AI threat models to defend against complex, multi-tenant deployments.

You will lead threat modeling, red teaming, and policy-as-code efforts, and work with architects to define agent Authority and sandboxing standards for secure execution.