Senior Software Development Engineer - GenAI

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.

Summary Our team owns the foundational AI/GenAI platform services that power CVS Health's internal agentic and LLM-driven tooling — including LLM routing and cost governance infrastructure, internal developer tooling for AI-assisted software development, retrieval-augmented generation (RAG) capabilities, and orchestration tools for building and deploying agentic workflows. We sit at the intersection of platform engineering and applied GenAI: we're responsible for making it fast, safe, and cost-effective for engineering teams across the enterprise to build with LLMs, while navigating the compliance realities of operating in a healthcare environment (PHI/PII handling, HIPAA, BAA requirements with model providers). This role will design and build core platform services — spanning areas like auth, quota/cost management, observability, and routing policy — and will help define what our next generation of foundational AI services looks like as the GenAI landscape evolves. The team is deeply senior and highly collaborative; we're looking for someone who brings genuine, self-driven enthusiasm for this space — someone who explores new ideas and tools because they're excited to, not because they were asked to — while working closely with the rest of the team to bring those ideas to life.

5+ years of professional software engineering experience, including 2+ years building production backend services in Python and/or TypeScript/Node.js 2+ years of experience designing and building RESTful APIs or microservices using frameworks such as FastAPI, Flask, Express, or NestJS Experience integrating with one or more LLM/AI provider APIs (e.g., Anthropic, OpenAI, AWS Bedrock, Google Vertex AI) in a production system Experience with at least one major cloud provider (AWS, Azure, or GCP) Experience with the following (or equivalents): Redis, Kafka, and MongoDB in a production environment Experience with OAuth2/OIDC or JWT-based authentication and authorization systems Experience with observability/telemetry tooling (e.g., OpenTelemetry, Prometheus, Grafana, Langfuse, Datadog) Experience with containerized applications (Docker) and CI/CD pipelines Experience with version control systems (Git) and code review processes Preferred Qualifications Genuine, self-motivated curiosity about GenAI and emerging AI infrastructure — someone who follows the space on their own and shows up with new ideas, tools, or approaches unprompted Strong team player who collaborates readily and shares ideas openly, even while operating on a team of senior engineers with established conventions Comfortable respectfully challenging established patterns and proposing alternatives as part of a collaborative team dynamic Prior experience building LLM/GenAI infrastructure itself (e.g., LLM gateways, agentic orchestration systems, RAG platforms) — not just consuming provider APIs, but designing the systems around them Ability to reason about system design trade-offs in distributed, stateful systems (e.g., cache invalidation, consumer group rebalancing, blue-green deployment of stateful services) Strong written and verbal communication skills, with the ability to explain technical trade-offs to both engineers and non-technical stakeholders Comfort operating with ambiguity and evolving requirements in a fast-moving technical landscape Experience or interest in prompt engineering, model routing strategies, or LLM cost optimization techniques Experience in a regulated industry