AI-Native Security Engineer - Senior

EY•Hartford, DC

3d•$106,900 - $200,600•Hybrid

About The Position

EY is hiring a Senior AI-Native Security Engineer for Challenger Core, which develops and maintains shared technology, methods, and risk and quality guardrails for EY’s next generation of AI-enabled services. The role makes AI systems that act across data, tools, and business processes defensible by embedding security throughout their lifecycle. The engineer will work with product and engineering teams, test controls under adversarial conditions, and develop reusable patterns, measurable coverage, clear evidence, and response practices. The position owns reusable AI security patterns, control objectives, reference architectures, and threat models; joins teams early to identify attack paths and shape controls; and designs boundaries for identity, access, isolation, approvals, and recovery. It also embeds security across data handling and software delivery, builds runtime protections and response capabilities, advises on residual risk, and develops shared implementations and guidance. The role is based anywhere in the country, requires up to 50% travel, and requires flexibility to work in the office in a hybrid capacity. The listed base salary ranges by location are $128,400–$192,500 in New York City, Boston, Washington, DC metro areas, Washington State, and Southern California; $133,600–$200,600 in Bay Area California offices; and $106,900–$176,500 in other U.S. office locations, including Sacramento. EY states that individual salaries depend on factors including education, experience, knowledge, skills, and geography. Benefits include medical and dental coverage, pension and 401(k) plans, flexible vacation, paid holidays, winter and summer breaks, personal/family care time, and other leaves of absence.

Requirements

At least 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.
Demonstrated ability to threat-model complex systems and translate attack paths into practical engineering measures.
Experience securing modern applications, cloud environments, identities, data, networks, and software delivery pipelines.
Working understanding of generative and agentic AI, including retrieval, model access, tool use, evaluation, and runtime behavior.
Hands-on experience building or extending security tests, controls, telemetry, reference implementations, or adversarial assessments.
Experience supporting vulnerability or incident response and translating lessons into stronger technical controls.
Record of partnering with engineers and risk functions to improve security while respecting user value and delivery constraints.
Ability to travel up to 50% and flexibility to work in the office in a hybrid capacity.
Strong foundations in application, cloud, platform, identity, data, and software delivery security.
Ability to reason about AI-specific attack paths and failure modes involving prompts, retrieval, agents, tools, users, and external services.
Experience translating threats into preventive, detective, and responsive measures that engineers can implement and operate.
Practical skill in red teaming, reproducible testing, vulnerability analysis, detection, and incident learning.
Ability to build security tests, controls, telemetry, and reference components and integrate them into delivery pipelines.
Clear communication and product judgment, including the ability to explain risk without drama, vagueness, or implied approval authority.

Nice To Haves

Experience securing tool-using agents, AI gateways, model-serving platforms, retrieval systems, or other high-autonomy applications.
Experience in regulated, safety-relevant, or multi-region environments with formal evidence and response requirements.
Experience designing behavioral analytics and investigation evidence for distributed or AI-enabled systems.
Experience assessing external AI services, dependencies, trusted artifacts, and exit or containment options.
Practical contributions to AI security research, responsible disclosure, open-source tooling, privacy technology, standards, or professional communities.

Responsibilities

Own reusable AI security patterns, control objectives, reference architectures, and threat models aligned with each use case’s risk and autonomy.
Work with product and engineering teams early to identify credible attack paths and shape controls that fit the product and delivery model.
Design practical patterns for identity, access, isolation, approvals, and recovery so tool-using AI operates within clear, enforceable boundaries.
Embed security across the data lifecycle, protecting confidentiality, integrity, provenance, permitted use, and monitored access.
Integrate automated security tests, policy gates, trusted artifacts, traceable changes, and safe rollback into engineering workflows.
Run focused red-team exercises against AI-specific abuse cases and turn findings into repeatable tests, stronger platform patterns, and actionable guidance.
Build runtime protection using end-to-end evidence and behavioral signals to detect abnormal actions, privilege misuse, attempted exfiltration, and degrading controls.
Support vulnerability triage and incident response with evidence, containment options, recovery actions, and lessons for future designs.
Provide concise technical recommendations to product, security, evaluation, and risk leaders while leaving approval and risk-acceptance decisions to accountable owners.
Create reference implementations, coach engineers, and turn production lessons into reusable controls.