Senior AI Security Engineer — Build Safe, Trusted AI

EY; McLean (VA); Hybrid; USD 107,000 - 193,000; Full time

Benefits offered by this job

Medical and dental coverage

Pension and 401(k)

Flexible vacation policy

Job summary

EY is seeking a Security Engineer to embed safety into AI lifecycles. You will collaborate with product and engineering teams to prove controls under adversarial conditions and replace ad‑hoc reviews with reusable patterns and measurable coverage.

The role emphasizes runtime protection, evidence-based decisions, and strong risk communications, with up to 50% travel and hybrid office options across US locations.

Qualifications

• Strong foundations in application, cloud, platform, identity, data, and software delivery security.
• Ability to model prompts, agents, tools, and external services to identify new attack paths.
• Experience translating threats into preventive, detective, and responsive measures.

Responsibilities

• Set the security direction and own reusable AI security patterns and threat models.
• Join builders early to shape controls that fit product and delivery models.
• Design practical patterns for identity, access, and recovery.
• Embed security across the data lifecycle and monitor access, provenance, and usage.
• Integrate automated security tests, policy gates, and trusted artifacts into workflows.
• Run focused red-team exercises and translate findings into repeatable tests.
• Develop runtime protection with evidence and behavioral signals to detect abuse.
• Support vulnerability triage and incidents with evidence and recovery actions.
• Provide concise technical risk recommendations to product and risk leaders.
• Create reference implementations and coach engineers to adopt reusable controls.

Skills

Security engineering

AI threat judgment

Control engineering

Adversarial mindset

Automation capability

Clear communication

Education

Bachelor’s Degree

Job description

EY is seeking a Security Engineer to embed safety into AI lifecycles. You will collaborate with product and engineering teams to prove controls under adversarial conditions and replace ad‑hoc reviews with reusable patterns and measurable coverage.

The role emphasizes runtime protection, evidence-based decisions, and strong risk communications, with up to 50% travel and hybrid office options across US locations.