Senior AI Security Engineer - Adversarial & Threat Modeling

EY; Detroit (MI); Ibrido; USD 107.000 - 177.000; Tempo pieno

Vantaggi offerti da questo lavoro

Total rewards package

Flexible vacation policy

Paid time off

Descrizione del lavoro

EY is seeking a security-leaning product and platform engineer to embed defense throughout AI lifecycles within the Challenger program. You’ll partner with product and engineering teams to prove controls under adversarial conditions and replace one-off reviews with reusable, measurable patterns.

The role focuses on designing scalable security patterns, running controlled tests, and delivering evidence-backed protections that enable ambitious AI use cases while reducing risk.

Competenze

• 5+ years of relevant experience.
• Bachelor’s Degree in a relevant field.
• Substantial experience in product, application, cloud, platform, or detection security, including hands‑on ownership of production controls.
• Threat modeling: assess complex systems and turn attack paths into practical engineering measures.
• Production security: secure modern apps, cloud environments, identities, data, and pipelines.
• AI systems knowledge: understanding of generative and agentic AI, including retrieval, model access, tool use, evaluation, and runtime behavior.
• Hands‑on automation: build or extend security tests, controls, telemetry, reference implementations, or adversarial assessments.
• Response experience: support vulnerability or incident response and translate lessons into stronger technical controls.
• Cross‑functional delivery: partner with engineers and risk functions to improve security while respecting user value and delivery constraints.
• Travel and On-site requirements: up to 50% travel and hybrid office presence.

Mansioni

• Set the security direction. Own reusable AI security patterns, control objectives, reference architectures, and threat models aligned to each use case.
• Join builders early. Work with teams before key design choices are fixed, identifying credible attack paths and shaping controls.
• Design scoped authority. Create practical patterns for identity, access, isolation, approvals, and recovery.
• Protect sensitive information. Embed security across the data lifecycle, preserving confidentiality and integrity.
• Secure the delivery path. Integrate automated security tests, policy gates, trusted artifacts, and safe rollback.
• Test adversarially. Run red-team exercises and translate findings into repeatable tests and stronger patterns.
• Build runtime protection. Use evidence and signals to detect abnormal actions and privilege misuse.
• Strengthen response. Support vulnerability triage and incidents with evidence and recovery actions.
• Advise on residual risk. Provide concise technical recommendations to product and risk leaders with accountable owners.
• Build shared capability. Create reference implementations and coach engineers to adopt safer patterns.

Conoscenze

Security engineering depth

AI threat judgment

Control engineering

Adversarial mindset

Automation capability

Pragmatic influence

Formazione

Bachelor's Degree

Descrizione del lavoro

EY is seeking a security-leaning product and platform engineer to embed defense throughout AI lifecycles within the Challenger program. You’ll partner with product and engineering teams to prove controls under adversarial conditions and replace one-off reviews with reusable, measurable patterns.

The role focuses on designing scalable security patterns, running controlled tests, and delivering evidence-backed protections that enable ambitious AI use cases while reducing risk.