Senior AI Security Architect

EY; Hartford (CT); Remote; USD 150,000 - 230,000; Full time

Benefits offered by this job

Medical and dental coverage

Total Rewards package

Flexible vacation policy

Job summary

EY is seeking an AI Security Engineer to own EY’s Agentic AI platform security end to end. You will define threat models, harden Kubernetes and infrastructure, and lead red-teaming to prove guardrails. The role spans policy-as-code, supply-chain integrity, and regulator-facing assurance.

You will collaborate with architecture to define authority, containment, and operational security contracts while delivering audit-grade evidence for regulated environments.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Security, or a related technical field, or demonstrably equivalent depth.
• 10+ years in security engineering, security engineering, or offensive security, including hands-on production ownership.
• Demonstrable depth in cloud-native and Kubernetes security: admission control, network policy, workload isolation, and runtime security in production.
• Practical experience securing AI or ML systems in production, including LLM/agentic surfaces like prompt injection and tool abuse.
• Threat modelling capability applied to real systems with verifiable controls.
• Audit-grade evidence delivery under compliance or regulatory constraints.
• Experience defining ownership boundaries and control contracts with platform, data, runtime, and delivery teams.

Responsibilities

• Own the platform threat model: agent autonomy, tool invocation, delegated authority, and data supply chain.
• Define security engineering and control set for every platform layer: Infrastructure, Kubernetes, identity, and sandboxing.
• Set secure-by-default contracts with hardened capabilities and templates.
• Defend against agentic threat classes including prompt injection and jailbreaks.
• Define agent authority models: delegated authority, scope limits, and non-escalation invariants.
• Own sandboxing standards for agent-generated code execution.
• Secure the model and knowledge supply chain: provenance, SBOM, attestation.
• Secure agent-to-agent and tool protocols with trust and authorization.
• Lead AI red teaming and adversarial testing with guardrails and enforcement.
• Own end-to-end supply-chain integrity, including signing and verification.
• Own admission and runtime policy across Kyverno and OPA, enforcing constraints.
• Define Kubernetes hardening baselines and tenant isolation testing.
• Serve as security authority in client engagements and regulator inquiries.
• Drive security detection and response with telemetry and incident playbooks.

Skills

Cloud-native security

AI threat models

Zero-trust foundations

Policy-as-code

Software supply-chain security

Offensive security

Risk pragmatism

Communication skills

Security enablement

Education

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

Tools

SPIFFE/SPIRE

Vault/OpenBao

PKI

Job description

EY is seeking an AI Security Engineer to own EY’s Agentic AI platform security end to end. You will define threat models, harden Kubernetes and infrastructure, and lead red-teaming to prove guardrails. The role spans policy-as-code, supply-chain integrity, and regulator-facing assurance.

You will collaborate with architecture to define authority, containment, and operational security contracts while delivering audit-grade evidence for regulated environments.