Lead AI Security Engineer: Defend the Agentic AI Platform

EY; Denver (CO); On-site; USD 126,000 - 230,000; Full time

Benefits offered by this job

Medical and dental coverage

401(k) with company match

Flexible vacation policy

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, sandboxing, supply-chain integrity, and policy-based controls across cloud-native infrastructure and agentic execution.

The candidate will lead defense against agentic threats, define the authority model, and drive red-teaming, build assurance artifacts for regulators, and engage with clients on security reviews.

Qualifications

• 10+ years in security engineering or offensive security with hands-on ownership.
• Demonstrable depth in cloud-native and Kubernetes security, including workload isolation and runtime security.
• Practical experience securing AI/ML systems in production and familiarity with agentic attack surfaces.

Responsibilities

• Own the platform threat model across deployment targets from cloud to air-gapped environments.
• Define security controls for infrastructure, Kubernetes, identities, and data protection.
• Lead defense against prompt injection, jailbreak and tool abuse across the agentic platform.
• Oversee security engineering reviews with clients, CISOs, and regulators and produce assurance artifacts.
• Drive security detection, telemetry, and incident response for the platform.

Skills

Cloud-native security

AI/agentic threat models

Zero trust

Policy-as-code

Software supply-chain security

Threat modelling

Client engagement

Education

Bachelor’s or Master’s in CS or related field

Tools

SPIFFE/SPIRE

PKI/certificate lifecycle

Sigstore/Cosign

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, sandboxing, supply-chain integrity, and policy-based controls across cloud-native infrastructure and agentic execution.

The candidate will lead defense against agentic threats, define the authority model, and drive red-teaming, build assurance artifacts for regulators, and engage with clients on security reviews.