Staff Machine Learning Engineer - Generative AI & Full-stack Applications

CVS Health CVS Health · Healthcare · Springfield, IL +52 · Innovation and Technology

Staff Machine Learning Engineer focused on building enterprise GenAI capabilities, including designing, prototyping, and productionizing AI-powered solutions. Responsibilities include integrating LLMs, implementing safety and compliance controls, building RAG pipelines, and developing evaluation harnesses. The role emphasizes full-stack development for AI applications and reusable component creation.

What you'd actually do

  1. Partner with stakeholders to identify, evaluate, document, and shape GenAI use cases (copilots, automation, decision support, and insight generation) with clear success metrics.
  2. Design solution architectures that integrate LLMs with enterprise systems, data sources, and tool/function calling while meeting latency and reliability expectations.
  3. Develop prototypes rapidly and validate them through evaluation, red-teaming, and user feedback; document tradeoffs and recommendations.
  4. Build production-grade services and full-stack experiences (APIs, UIs, workflows) with secure authentication/authorization, audit logging, and scalable deployment patterns.
  5. Implement safety, privacy, and compliance controls (e.g., PHI/PII protection, prompt injection defenses, data residency constraints, and policy-based filtering).

Skills

Required

  • 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.
  • Python
  • backend services
  • APIs
  • modern web application development
  • reliability
  • security
  • LLM application patterns: RAG, tool/function calling, prompt management, evaluation, and guardrails
  • common ML libraries
  • serving frameworks
  • containerization
  • Kubernetes
  • CI/CD
  • infrastructure-as-code concepts
  • production observability

Nice to have

  • Strong full-stack engineering skills
  • Ability to communicate clearly, influence across teams, and translate business needs into implementable technical plans.

What the JD emphasized

  • building and operating production services
  • demonstrated hands-on GenAI delivery (LLMs, RAG, evaluation, and safety controls)
  • delivering solutions in high-scale, high-availability environments with strong security and compliance requirements
  • safety, privacy, and compliance controls
  • PHI/PII protection
  • prompt injection defenses
  • data residency constraints
  • policy-based filtering

Other signals

  • building enterprise AI/ML capability
  • designing and prototyping AI-powered solutions
  • evolving them into secure, resilient, enterprise-ready products
  • GenAI use cases (copilots, automation, decision support, and insight generation)
  • integrate LLMs with enterprise systems, data sources, and tool/function calling
  • Develop prototypes rapidly and validate them through evaluation, red-teaming, and user feedback
  • Build production-grade services and full-stack experiences
  • Implement safety, privacy, and compliance controls
  • Instrument solutions end-to-end with metrics, traces, logs, and model/app observability
  • Build and maintain evaluation harnesses for LLM quality, safety, and business outcomes
  • Implement RAG pipelines
  • Collaborate with platform teams on deployment, monitoring, drift/quality detection, and incident response
  • Contribute reusable libraries and patterns for prompt management, retrieval, tool calling, and policy enforcement
  • Continuously improve developer experience through templates, CI/CD automation, and documentation