AI Security Architect – Agentic Platform Defense

EY; Palo Alto (CA); On-site; USD 157,000 - 262,000; 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. You will shape threat models, deploy secure-by-default controls, and lead red teaming across cloud-native environments. This role requires deep AI security expertise, zero-trust foundations, and strong communication with clients and regulators.

You will define policy-as-code, secure the supply chain, and drive incident response and assurance artifacts for regulated deployments.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Security, or a related field or demonstrably equivalent depth.
• 10+ years in security engineering with hands-on production ownership.
• Deep cloud-native and Kubernetes security experience in production.
• Hands-on workload identity and secrets management expertise.
• Practical experience securing AI or ML systems in production with agentic risk.

Responsibilities

• Own platform threat model covering agent autonomy, tool invocation, and multi- tenancy.
• Define security controls for all platform layers: infra, Kubernetes, identity, and data.
• Set secure-by-default contracts with templates, charts, and network policy.
• Lead defense against agentic threat classes and prompt injection risks.
• Define agent authority model with delegation limits and non-escalation invariants.
• Own sandboxing standards for agent-generated code execution and isolation.
• Secure model and knowledge supply chain with provenance and attestation.
• Secure agent-to-agent and tool protocols with trust and authorization.
• Lead AI red teaming, adversarial testing, and guardrails validation.
• Own end-to-end supply-chain integrity: Sigstore/Cosign, SBOM, attestation.
• Own admission and runtime policy using Kyverno and OPA; enforce guards.
• Define Kubernetes hardening baselines and network controls.
• Ensure tenant isolation and cross-tenant leakage prevention.
• Serve as security lead in client engagements with CISOs/regulators.
• Drive detection and response for platform misbehavior and incidents.

Skills

Cloud-native security

Kubernetes security

AI and agentic threat models

Zero-trust / workload identity

Policy-as-code

Software supply-chain security

Threat modelling

Communication with execs/regulators

Education

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

Tools

SPIFFE/SPIRE

PKI / certificate lifecycle

Sigstore / Cosign

Kyverno / OPA

Kuberenetes security tooling

SBOM / provenance tooling

Job description

EY is seeking an AI Security Engineer to own the security posture of EY’s Agentic AI platform end to end. You will shape threat models, deploy secure-by-default controls, and lead red teaming across cloud-native environments. This role requires deep AI security expertise, zero-trust foundations, and strong communication with clients and regulators.

You will define policy-as-code, secure the supply chain, and drive incident response and assurance artifacts for regulated deployments.