AI 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 us 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.

Position Summary 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 us accountable and prioritize safety and quality in everything we do. We are seeking an AI Engineer to design, build, and deploy GenAI/agentic solutions that support enterprise business needs.

In this hands‑on role, you will develop agentic frameworks, data pipelines, and retrieval‑augmented and agent‑based applications as part of an engineering team, working under the guidance of senior and staff engineers. You will develop well‑defined features and components from conception through production support, while growing your depth in ML engineering, cloud platforms, and responsible AI practices.

• Build GenAI and agentic AI components, including RAG pipelines, tool‑calling agents, agent memory, and multi‑agent workflows, using vector databases and graph retrieval patterns.
• Develop and maintain data pipelines for ingestion, transformation, and feature preparation using Python, SQL, and PySpark across Big Query, PostgreSQL, MongoDB, and Elasticsearch.
• Implement computer vision solutions such as object detection and tracking using OpenCV, Roboflow, including dataset preparation and annotation workflows.
• Apply statistical and unsupervised techniques to support analytics, segmentation, and causal‑impact use cases.
• Build workflow automations and integrations on cloud services.
• Write clean, tested, and well‑documented code; participate in code reviews and follow established CI/CD, security, and compliance standards.
• Monitor model and agent performance in production, and help troubleshoot issues such as data drift, retrieval quality, latency, and failures.
• Support evaluation of model and agent quality using defined metrics, test sets, and human‑in‑the‑loop review.
• Collaborate with product owners, data engineers, and senior engineers to translate requirements into technical tasks, and communicate progress, blockers, and risks clearly.
• Contribute to team knowledge‑sharing and stay current with emerging AI/ML tools and techniques, including AI‑assisted development.

• 2+ years of hands‑on experience developing and deploying machine learning or AI applications.
• 2+ years of experience with Python, including building production‑quality code and APIs (e.g., FastAPI or Flask).
• 2+ years of experience with SQL and experience working with relational and/or No
  
  SQL databases.
• 2+ years of hands‑on experience with at least one deep learning framework (PyTorch, Tensor Flow, or Keras).
• 2+ years of experience working with core AI/ML concepts, including model training, validation, evaluation metrics, and feature engineering.
• 1+ year of hands‑on experience building or contributing to GenAI solutions, including RAG and LLM integration (e.g., prompt design, tool calling, embeddings).
• 1+ year of experience with a vector database (e.g., Pinecone or Qdrant) or a comparable search/retrieval technology.
• 1+ year of experience working on a cloud platform (GCP/Azure preferred; AWS acceptable), including storage, compute, and basic IAM concepts.
• 1+ year of experience with Git and collaborative development…