Senior AI Security Engineer: Defend AI Systems

EY; Phoenix (AZ); Hybrid; USD 107,000 - 201,000; Full time

Job summary

EY Challenger is seeking a security-focused engineer to embed robust AI security throughout the lifecycle. You will translate threats into practical controls, work with product and engineering teams, and build reusable patterns to defend ambitious AI use cases.

You will lead adversarial testing, design practical identity and access controls, and contribute to scalable security patterns across EY’s Challenger initiatives.

Qualifications

• 5+ years of relevant experience.
• Experience securing modern applications, cloud environments, identities, data, networks, and software delivery pipelines.
• AI systems knowledge: working understanding of generative and agentic AI, including retrieval, model access, tool use, evaluation, and runtime behavior.
• Hands-on automation: experience building or extending security tests, controls, telemetry, reference implementations, or adversarial assessments.
• Threat modeling: demonstrated ability to assess complex systems and turn attack paths into practical engineering measures.
• Cross-functional delivery: partnering 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.

Responsibilities

• Set the security direction. Own reusable AI security patterns, control objectives, reference architectures, and threat models aligned to the risk and autonomy of 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 so tool-using AI acts within clear boundaries.
• Protect sensitive information. Embed security across the data lifecycle, preserving confidentiality, integrity, provenance, permitted use, and monitored access.
• Secure the delivery path. Integrate automated security tests, policy gates, trusted artifacts, traceable changes, and safe rollback into engineering workflows.
• Test adversarially. Run red-team exercises against AI-specific abuse cases and convert findings into repeatable tests and stronger platform patterns.
• Build runtime protection. Use end-to-end evidence and behavioral signals to detect abnormal actions and privilege misuse.
• Strengthen response. Support vulnerability triage and incidents with clear evidence and recovery actions.
• Advise on residual risk. Give concise technical recommendations while keeping risk acceptance with accountable owners.
• Build shared capability. Create reference implementations, coach engineers, and turn lessons into reusable controls.

Skills

Security engineering depth

AI threat judgment

Control engineering

Adversarial mindset

Automation capability

Pragmatic influence

Education

Bachelor’s Degree in a relevant field

Job description

EY Challenger is seeking a security-focused engineer to embed robust AI security throughout the lifecycle. You will translate threats into practical controls, work with product and engineering teams, and build reusable patterns to defend ambitious AI use cases.

You will lead adversarial testing, design practical identity and access controls, and contribute to scalable security patterns across EY’s Challenger initiatives.