Principal AI Security Engineer for Agentic Platform

EY; Las Vegas (NV); Remote; USD 126,000 - 230,000; Full time

Benefits offered by this job

Medical and dental coverage

Pension and 401(k)

Paid time off

Flexible vacation policy

Job summary

EY seeks an AI Security Engineer to own the security posture of its agentic AI platform end to end, from silicon-level attestation to policy enforcement. You’ll define threat models, implement secure-by-default controls, and lead red teaming against novel AI threats in regulated environments.

The role requires deep cloud-native security and hands-on experience with Kubernetes, AI threats, and policy-as-code.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Security, or a related technical field.
• 10+ years in security engineering with production ownership.
• Hands-on experience securing AI/ML systems in production, including prompt injection, tool abuse, and data risk.
• Experience defining ownership boundaries and control contracts with platform, data, runtime, and delivery teams.

Responsibilities

• Own the platform threat model across deployment targets and platform layers.
• Define security engineering and control sets for all platform layers: infra, Kubernetes, identity, and data.
• Set secure-by-default contracts including agent templates, Helm charts, and policies.
• Lead defense against agentic threat classes including prompt injection and tool abuse.
• Define agent authority models and containment boundaries.
• Own sandboxing standards for safe code execution and boundary testing.
• Secure the model and knowledge supply chain (SBOM, provenance, signing).
• Secure inter-agent and tool protocols with trust and authorization.
• Lead AI red teaming and adversarial testing before auditors.
• Own end-to-end supply-chain integrity and attestation (Sigstore, SBOM).
• Own admission and runtime policy across Kyverno and OPA.
• Define Kubernetes hardening baselines and tenant isolation assurances.
• Serve as security authority in client engagements and regulatory reviews.
• Drive security detection and response for agentic platforms.

Skills

Cloud-native security

Kubernetes security

AI security

Threat modelling

Policy-as-code

Red teaming

Supply-chain security

Incident response

Zero-trust

Regulatory security

Education

Bachelor’s or Master’s degree in Computer Science, Security, or related

Tools

Sigstore/Cosign

Notation

Kyverno

OPA

Job description

EY seeks an AI Security Engineer to own the security posture of its agentic AI platform end to end, from silicon-level attestation to policy enforcement. You’ll define threat models, implement secure-by-default controls, and lead red teaming against novel AI threats in regulated environments.

The role requires deep cloud-native security and hands-on experience with Kubernetes, AI threats, and policy-as-code.