Position: Staff Machine Learning Engineer - Generative AI & Full-Stack Applications
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.
At CVS Health, our purpose is to deliver better health outcomes by meeting consumers where they are—through local care, digital experiences, and a nationwide team committed to quality, safety, and affordability.
Our Solutions Engineering and Infrastructure organization is building an enterprise AI/ML capability that delivers reliable, responsible, and secure AI‑powered platforms and solutions at Fortune 5 scale, and this role is foundational to help us develop that capability.
This is a senior individual-contributor role, focused on identifying evaluating and documenting high-value use cases, designing and prototyping AI-powered solutions, and evolving them into secure, resilient, enterprise‑ready products and platform components.
Key Responsibilities:
AI Solution Design & Prototyping
- Partner with stakeholders to identify, evaluate, document, and shape GenAI use cases (copilots, automation, decision support, and insight generation) with clear success metrics.
- Design solution architectures that integrate LLMs with enterprise systems, data sources, and tool/function calling while meeting latency and reliability expectations.
- Develop prototypes rapidly and validate them through evaluation, red‑teaming, and user feedback; document tradeoffs and recommendations.
Production Engineering & Enterprise Readiness
- Build production‑grade services and full‑stack experiences (APIs, UIs, workflows) with secure authentication/authorization, audit logging, and scalable deployment patterns.
- Implement safety, privacy, and compliance controls (e.g., PHI/PII protection, prompt injection defenses, data residency constraints, and policy‑based filtering).
- Instrument solutions end‑to‑end with metrics, traces, logs, and model/app observability; contribute to SLOs, error budgets, and operational runbooks.
Model Enablement & Evaluation
- Build and maintain evaluation harnesses for LLM quality, safety, and business outcomes (offline tests, golden sets, regression suites, and online experiments).
- Implement RAG pipelines (chunking, embedding, vector search, reranking) and optimize for accuracy, cost, and latency.
- Collaborate with platform teams on deployment, monitoring, drift/quality detection, and incident response for model‑backed services.
Reusable Components & Engineering Excellence
- Contribute reusable libraries and patterns for prompt management, retrieval, tool calling, and policy enforcement.
- Participate in design reviews and code reviews; mentor senior and mid‑level engineers on GenAI engineering practices.
- Continuously improve developer experience through templates, CI/CD automation, and documentation that accelerates safe adoption.
Required Qualifications:
- 7+ years of software engineering supporting Data or AI/ML initiatives, including building and operating production services.
- 3+ years applying ML/AI in production; demonstrated hands‑on GenAI delivery (LLMs, RAG, evaluation, and safety controls)
- 3+ years of experience delivering solutions in high‑scale, high‑availability environments with strong security and compliance requirements.
Preferred Qualifications
- Strong full‑stack engineering skills (backend services, APIs, and modern web application development) with a focus on reliability and security.
- Hands‑on expertise with LLM application patterns: RAG, tool/function calling, prompt management, evaluation, and guardrails.
- Experience with Python and at least one additional backend language; familiarity with common ML libraries and serving frameworks.
- Working knowledge of containerization and Kubernetes, CI/CD, infrastructure‑as‑code concepts, and production observability.
- Ability to communicate clearly, influence across teams, and translate business needs into implementable technical plans.
Education: