Principal Application Security Engineer – AI & Agentic Systems

CVS Health•New York, NY

4d•$144,200 - $288,400

About The Position

We’re building a world of health around every individual — shaping a more connected, convenient and compassionate health experience. At CVS Health®, you’ll be surrounded by passionate colleagues who care deeply, innovate with purpose, hold ourselves accountable and prioritize safety and quality in everything we do. Join us and be part of something bigger – helping to simplify health care one person, one family and one community at a time.

Requirements

10+ years of experience designing, building, and securing large-scale applications and platforms.
7+ years of expertise in application security, including threat modeling, secure design, and vulnerability management.
7+ years of programming experience in one or more languages such as Python, Java, JavaScript, C#, or Go.
5+ years of experience of developing and securing AI and ML workloads, with recent experience in generative AI and agentic workloads.
5+ years of experience public cloud platforms (AWS, Azure, and/or GCP) and modern application architectures.
3+ years of experience with containerized, serverless, and microservice-based architectures.

Nice To Haves

Hands-on experience securing AI agents, RAG pipelines, and tool-using LLM systems.
Proven ability to lead complex security initiatives from concept through enterprise-scale adoption.
Familiarity with AI governance, responsible AI principles, and emerging AI security standards.
Experience integrating security controls into CI/CD pipelines for AI and application workloads.
Strong understanding of compliance frameworks (PCI, HIPAA, NIST, HITRUST, CSA).
Experience influencing security strategy beyond a single team, including enterprise or platform-level impact.
Contributions to security research, open-source projects, or industry communities.

Responsibilities

Lead development and enforcement of application and AI security policies, standards, and guardrails, embedding security-by-design across both traditional and AI-driven systems.
Establish secure design patterns for AI agent frameworks, covering prompt management, tool invocation, memory handling, autonomy boundaries, and escalation controls.
Promote organization-wide awareness of AI-specific risks such as model misuse, prompt injection, data leakage, and unsafe agent behavior.
Serve as the principal SME for securing AI-enabled applications and agentic system architectures.
Architect and review secure designs for systems leveraging LLMs/foundation models, autonomous and semi-autonomous agents, RAG pipelines, and tool‑using or decision‑making workflows.
Define identity, authorization, data access, and observability controls specific to agentic environments while partnering closely with AI platform, product, and data teams to ensure responsible AI delivery.
Influence engineering and product teams to integrate secure engineering practices and align security with compliance, privacy, and responsible AI initiatives.
Advise senior leadership on AI security implications, architectural decisions, and long-term strategy while shaping roadmaps that anticipate emerging AI threats and regulatory requirements.
Lead advanced security testing and risk assessments for AI-enabled systems, including threat modeling of agent workflows, abuse/misuse analysis, and secure design reviews of AI pipelines.
Evaluate and guide adoption of new AI security tools, ensuring protections maintain confidentiality, integrity, availability, and responsible data use.
Provide senior technical leadership during incidents involving application or AI systems, guiding response strategies for misuse, data exposure, and autonomous failures.
Translate operational learnings into improved security architecture, controls, and system resilience.
Mentor senior and principal engineers to elevate security maturity across the organization.
Contribute to research and evaluation of emerging AI security practices and play a key role in shaping the long-term application and AI security roadmap, advocating for security as a strategic accelerator for AI adoption.