Senior AI Security Engineer: Build Safer AI Systems

EY; San Jose (CA); Hybrid; USD 134,000 - 201,000; Full time

Benefits offered by this job

Medical and dental coverage

Pension and 401(k)

Paid time off

Flexible vacation policy

Job summary

EY is seeking a security-focused Challenger role in the US Bay Area to embed security across AI systems and product lifecycles. You will develop reusable patterns, threat models, and practical controls, working with product and engineering to defend complex AI use cases under adversarial conditions.

You’ll drive end-to-end security testing, automate controls, and articulate risk and evidence for leaders while enabling safe, scalable delivery across cloud environments and data lifecycles.

Qualifications

• 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: ability to assess complex systems and turn attack paths into practical engineering measures.
• Production security: securing modern applications, cloud environments, identities, data, and pipelines.
• AI systems knowledge: working understanding of generative and agentic AI, including retrieval, model access, tool use, evaluation, and runtime behavior.
• Hands‑on automation: building or extending security tests, telemetry, and reference implementations.
• Response experience: support vulnerability or incident response and translate lessons into stronger controls.
• Cross‑functional delivery: partnering with engineers and risk functions to improve security while respecting user value.

Responsibilities

• Set the security direction and own reusable AI security patterns, control objectives, reference architectures, and threat models.
• Join builders early and shape controls before key design choices are fixed.
• Design scoped authority for identity, access, isolation, approvals, and recovery.
• Protect sensitive information across the data lifecycle with confidentiality and integrity.
• Secure the delivery path by integrating automated security tests and trusted artifacts.
• Test adversarially with red-team exercises and convert findings into repeatable tests and patterns.
• Build runtime protection using signals to detect abnormal actions and privilege misuse.
• Strengthen response with clear evidence and containment options.
• Advise on residual risk with concise technical recommendations.
• Build shared capability with reusable controls and coached engineers.

Skills

Security engineering

AI threat judgment

Control engineering

Adversarial mindset

Automation capability

Pragmatic influence

Education

Bachelor’s Degree

Tools

None

Job description

EY is seeking a security-focused Challenger role in the US Bay Area to embed security across AI systems and product lifecycles. You will develop reusable patterns, threat models, and practical controls, working with product and engineering to defend complex AI use cases under adversarial conditions.

You’ll drive end-to-end security testing, automate controls, and articulate risk and evidence for leaders while enabling safe, scalable delivery across cloud environments and data lifecycles.