Senior AI Security Engineer Platform Defense Lead

EY; Hartford (CT); Remote; USD 140,000 - 190,000; 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 from cloud to edge. The role covers threat modeling, secure-by-default contracts, sandboxing, and rigorous defense across the data and execution stack, including model provenance and policy enforcement.

The ideal candidate will lead AI red teaming, define agent authority models, and work with architecture to ensure regulator-ready security controls across Kubernetes, supply chain, and runtime

Responsibilities

• Own the platform threat model covering agent autonomy, tool invocation, delegated authority, data supply chain, multi-tenancy from cloud to air-gapped.
• Define the security engineering and control set for every platform layer: infra, Kubernetes, identity, secrets, secure execution and sandboxing, data flow, telemetry.
• Set the secure-by-default contract so platform capabilities arrive hardened with templates, Helm charts, sandbox profiles, and network policy.
• Defend against agentic threat classes including prompt injection, jailbreak, excessive agency, and retrieval-augmented data exfiltration.
• Define the agent authority model with delegated authority, scope limits, consent boundaries, and non-escalation invariants.
• Own the sandboxing security standard for agent-generated code: isolation, scope, egress restrictions, and boundary tests.
• Secure the model and knowledge supply chain: provenance, registry governance, poisoning risk, and vector-store integrity.
• Secure agent-to-agent and tool protocols: discovery trust, tool registration, and inter-agent call authorization.
• Lead AI red teaming and adversarial testing with guardrails, sandboxes, and authority boundaries.
• Own supply-chain integrity end-to-end: signing, attestation, SBOM, provenance, and license governance.
• Own admission and runtime policy: policy-as-code, signature-verification, Pod Security Standards, and guardrails.

Job description

EY is seeking an AI Security Engineer to own the security posture of EY’s Agentic AI platform end to end from cloud to edge. The role covers threat modeling, secure-by-default contracts, sandboxing, and rigorous defense across the data and execution stack, including model provenance and policy enforcement.

The ideal candidate will lead AI red teaming, define agent authority models, and work with architecture to ensure regulator-ready security controls across Kubernetes, supply chain, and runtime