Remote AI Security Engineer – Agentic Platform Defense

EY; Indianapolis (IN); On-site; USD 126,000 - 230,000; Full time

Benefits offered by this job

Total rewards package

Healthcare and retirement plans

Flexible vacation policy

Tuition reimbursement

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 define threat models, build hardened controls, and defend against prompt injection, tool abuse, and advanced attacks across the stack.

The role spans from silicon-level attestation to policy enforcement, with red-teaming, supply-chain integrity, and audit-grade evidence. Strong cloud-native and AI security expertise are expected.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Security, or a related technical field
• 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 familiarity with LLM and agentic attack surfaces such as prompt injection, tool abuse, excessive agency, and data supply-chain risk

Responsibilities

• Own the platform threat model: covering agent autonomy, tool invocation, delegated authority, model and data supply chain, multi-tenancy, across all deployment targets
• Define the security engineering and control set for every platform layer: infrastructure, Kubernetes, identity, secrets, secure execution, telemetry
• Set the secure-by-default contract so platform capabilities arrive hardened with templates, sandbox profiles, and network policies
• Own defense against agentic threat classes including prompt injection, jailbreak, excessive agency, and authority escalation
• Define agent authority model: delegated and on-behalf-of authority, scope and delegation-depth limits, consent boundaries
• Own the sandboxing security standard for agent-generated code execution: isolation, scope, and tests
• Secure the model and knowledge supply chain: provenance, SBOM, intake governance
• Secure agent-to-agent and tool protocols: discovery trust, tool registration, schema validation, authorization
• Lead AI red teaming and adversarial testing with guardrails, sandboxes, authority boundaries
• Own supply-chain integrity end-to-end: Sigstore/Cosign, SBOM, provenance, CVE management
• Own admission and runtime policy: policy-as-code across Kyverno and OPA
• Define Kubernetes and infrastructure hardening baselines: CIS-aligned config, network deny, secrets handling
• Own tenant isolation assurance and cross-tenant leakage testing
• Serve as security authority in client engagements: security reviews, regulator responses, assurance artefacts
• Drive security detection and response: telemetry, alerts, playbooks, post-incident reviews

Skills

Cloud-native security

Kubernetes security

AI threat models

Policy-as-code

SBOM/provenance

Threat modelling

Red teaming

Supply-chain security

Agentic security

Education

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

Tools

SPIFFE/SPIRE

Vault

PKI 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 define threat models, build hardened controls, and defend against prompt injection, tool abuse, and advanced attacks across the stack.

The role spans from silicon-level attestation to policy enforcement, with red-teaming, supply-chain integrity, and audit-grade evidence. Strong cloud-native and AI security expertise are expected.