Senior AI Security Architect - Platform Defender

EY; Annapolis (MD); Remote; USD 126,000 - 262,000; Full time

Job summary

EY seeks an AI Security Engineer to own the security posture of EY’s Agentic AI platform end to end, spanning silicon-level attestation to prompt-injection defense and audit-grade evidence. You will define threat models, implement secure-by-default contracts, and lead red-teaming against agentic threats in regulated environments.

The role demands deep cloud-native security expertise, experience with AI security, and the ability to communicate security risk to CISOs and regulators.

Qualifications

• Bachelor's or Master's degree in Computer Science, Security, or related technical field, or demonstrably equivalent depth.
• 10+ years in security engineering, including hands-on production ownership.
• Demonstrable depth in cloud-native and Kubernetes security: admission control, network policy, workload isolation, and runtime security in production.
• Hands-on experience with workload identity and secrets management (SPIFFE/SPIRE, Vault/OpenBao or equivalents) and with PKI and certificate lifecycle.
• Practical experience securing AI or ML systems in production, including familiarity with LLM and agentic attack surfaces, such as prompt injection, tool abuse, excessive agency, and model or data supply-chain risk.
• Threat modelling capability applied to real systems, with evidence that the resulting controls were built and verified.
• A track record delivering under compliance, security, or regulatory constraint with audit-grade evidence requirements.
• Experience defining ownership boundaries and control contracts with platform, data, runtime, and delivery teams.
• Experience building or leading an AI red team, or running adversarial testing against LLM and agentic systems.
• Exposure to regulated industries: financial services, tax, audit, healthcare, or public sector.

Responsibilities

• Own the platform threat model covering agent autonomy, tool invocation, delegated authority, model and data supply chain, multi-tenancy, for all deployment targets.
• Define the security engineering and control set for every platform layer: infrastructure, Kubernetes, identity and secrets, secure execution, sandboxing, gateway, data, telemetry.
• Set the secure-by-default contract so platform capabilities arrive hardened with correct controls.
• Own defense against agentic threat classes including prompt injection, jailbreak, and authority-escalation attacks.
• Work with the architecture team to define the agent authority model and non-escalation invariant.
• Own the sandboxing security standard for agent-generated code execution: isolation, scope, egress, containment, and tests.
• Secure the model and knowledge supply chain: provenance, registry governance, poisoning risk, SBOM, attestation.
• Secure agent-to-agent and tool protocols: discovery trust, tool registration, schema validation, and inter-agent authorization.
• Lead AI red teaming and adversarial testing to validate guardrails and boundaries.
• Own supply-chain integrity end to end: artifact signing, SBOM, provenance, CVE management, and license governance.
• Own admission and runtime policy: policy-as-code across Kyverno and OPA, signature-verification, and Pod Security Standards.
• Define Kubernetes and infrastructure hardening baselines: CIS-aligned configurations, network policy, secret handling.
• Own tenant isolation assurance: tenant boundary testing across compute, network, storage, telemetry, and evidence.
• Serve as the security authority in client engagements: security reviews, regulator responses, and assurance artefacts.
• Drive security detection and response: threat detection, telemetry, alerting, and incident response playbooks.

Skills

Kubernetes security

Cloud security

Threat modelling

Policy-as-code

AI security

Adversarial testing

Security architecture

Communication with executives

Education

Bachelor's or Master's in CS/Security

Tools

Sigstore/Cosign

Notation

OPA/Kyverno

Kubernetes security tooling

Job description

EY seeks an AI Security Engineer to own the security posture of EY’s Agentic AI platform end to end, spanning silicon-level attestation to prompt-injection defense and audit-grade evidence. You will define threat models, implement secure-by-default contracts, and lead red-teaming against agentic threats in regulated environments.

The role demands deep cloud-native security expertise, experience with AI security, and the ability to communicate security risk to CISOs and regulators.