Senior AI Security Architect & Platform Assurance Leader

EY; Salt Lake City (UT); Remote; USD 140,000 - 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 covers threat modeling, security engineering, and defense against advanced agentic threats across cloud-native stacks.

The candidate will lead red teaming, policy-as-code, and supply-chain integrity, working with architecture to define agent authority models and sandboxing standards for secure code execution. Location flexible within the United States.

Qualifications

• Experience in threat modelling of complex platform architectures.
• Deep security engineering expertise across cloud-native stacks.
• Proficiency in practical AI/agentic threat modeling and risk assessment.

Responsibilities

• Own the platform threat model across deployment targets from cloud to air-gapped.
• Define the security engineering and control set for infrastructure, Kubernetes, identity, and secure execution.
• Set secure-by-default contracts including agent templates, Helm charts, and network policy.
• Defend against agentic threat classes including prompt injection and jailbreaks.
• Collaborate with architecture to define the agent authority model and non-escalation invariants.
• Own sandboxing standards for agent-generated code execution and data isolation.
• Secure model and knowledge supply chains, provenance, and attestation.
• Define policies across Kyverno and OPA and enforce guardrails.
• Lead AI red teaming and adversarial testing cadence before auditors or adversaries.

Skills

Threat modelling

Kubernetes security

Cloud security

Policy-as-code

Red team testing

AI security

Tools

Sigstore/Cosign

Notary/SBOM tooling

Kyverno

OPA (Open Policy Agent)

Kuberenetes

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 covers threat modeling, security engineering, and defense against advanced agentic threats across cloud-native stacks.

The candidate will lead red teaming, policy-as-code, and supply-chain integrity, working with architecture to define agent authority models and sandboxing standards for secure code execution. Location flexible within the United States.