Staff Application Security Engineer – AI & Agentic Systems

CVS Health•New York, NY

2d•$106,605 - $284,280

About The Position

We are seeking a Staff Application Security Engineer – AI & Agentic Systems to help secure the next generation of AI-enabled applications, large language model integrations, and agentic systems. This role will partner closely with engineering, product, platform, and data teams to embed security into the design, development, and operation of both traditional and AI-driven solutions. As a senior technical contributor, you will help define secure design patterns, conduct threat modeling and risk assessments, guide engineering teams on secure development practices, and support the adoption of responsible AI security controls across the enterprise.

Requirements

7+ years of experience designing, building, or securing enterprise-scale applications and platforms.
5+ years of application security experience, including threat modeling, secure design, code review, and vulnerability management.
5+ years of programming experience in one or more languages such as Python, Java, JavaScript, C#, or Go.
3+ years of experience developing or securing AI, machine learning, or generative AI solutions.
3+ years of experience with public cloud platforms including AWS, Azure, or Google Cloud Platform.

Nice To Haves

Experience securing modern application architectures, including APIs, containers, microservices, and serverless technologies.
Strong understanding of secure software development lifecycle practices and application security testing methodologies.
Hands-on experience securing AI agents, retrieval augmented generation solutions, and large language model integrations.
Experience conducting threat modeling and security assessments for AI-enabled systems.
Familiarity with responsible AI principles, AI governance, and emerging AI security frameworks.
Experience integrating security controls into continuous integration and continuous delivery pipelines.
Knowledge of common compliance frameworks such as PCI DSS, HIPAA, NIST, HITRUST, and CSA.
Ability to influence technical decisions across multiple teams and organizations.
Experience contributing to security research, open-source projects, or industry communities.

Responsibilities

Develop and maintain application and AI security standards, best practices, and guardrails.
Promote secure-by-design principles across application and AI development lifecycles.
Establish secure design patterns for AI agents, prompt management, tool integrations, memory handling, and autonomous workflows.
Partner with engineering teams to identify and mitigate AI-specific security risks such as prompt injection, model abuse, data leakage, and unauthorized agent actions.
Serve as a subject matter expert supporting the security of AI-enabled applications and agentic systems.
Review and provide guidance on architectures utilizing large language models, retrieval augmented generation pipelines, AI agents, and AI-powered workflows.
Define and recommend identity, authorization, data protection, observability, and governance controls for AI environments.
Collaborate with AI platform, engineering, product, and data teams to ensure secure and responsible AI adoption.
Perform threat modeling, architecture reviews, and security assessments for applications and AI-enabled systems.
Conduct security analysis of AI workflows, model integrations, agent interactions, and data flows.
Partner with engineering teams to prioritize and remediate security findings.
Evaluate emerging AI security tools and technologies to improve organizational security posture.
Influence engineering teams to integrate security controls into development processes and product roadmaps.
Partner with privacy, compliance, legal, and risk teams to align security controls with organizational requirements.
Provide guidance on AI security considerations, emerging threats, and industry best practices.
Participate in strategic initiatives supporting secure AI adoption across the enterprise.
Support investigation and response efforts involving application and AI-related security events.
Assist in identifying root causes and implementing long-term security improvements.
Drive continuous improvement of security controls, processes, and engineering practices.
Mentor security engineers and development teams on secure coding, threat modeling, and AI security best practices.
Contribute to the evaluation of emerging AI security research, technologies, and industry standards.
Help advance the organization's application and AI security strategy through innovation and technical leadership.