Senior Al Engineer

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.

Designs, develops, and implements Artificial Intelligence (AI) and Generative AI solutions across the affiliate line of business by applying advanced software engineering and machine learning expertise. Builds, deploys, and supports scalable AI applications, cloud-native services, and intelligent automation solutions while collaborating with cross-functional teams to deliver business value in a secure and responsible manner. Leverages technologies such as AWS Bedrock, GCP Vertex AI, Retrieval-Augmented Generation (RAG), agentic AI frameworks, and cloud-native architectures to solve complex business challenges.

• Designs, develops, and deploys AI and Generative AI applications using cloud-native services and modern software engineering practices.
• Builds and maintains AI-powered solutions utilizing technologies such as AWS Bedrock, GCP Vertex AI, large language models (LLMs), and machine learning frameworks.
• Develops Retrieval-Augmented Generation (RAG) systems, including document ingestion, vector search, embeddings, and retrieval pipelines to integrate enterprise knowledge into AI applications.
• Creates, tests, and optimizes prompts, workflows, and agentic AI solutions using technologies such as Bedrock Agents, Vertex AI Agent Builder, Lang Chain, Lang Graph, Llama Index, or similar frameworks.
• Develops APIs, microservices, and event-driven integrations that enable scalable and secure AI capabilities across enterprise platforms.
• Collaborates with product owners, engineers, data teams, security teams, and business stakeholders to gather requirements, recommend solutions, and deliver AI capabilities that meet business objectives.
• Writes and executes comprehensive test cases, performs debugging, conducts code reviews, monitors production performance, and resolves issues to ensure reliability and quality.
• Participates in model evaluation, deployment, monitoring, and optimization activities to improve performance, accuracy, latency, scalability, and cost efficiency.
• Implements AI solutions in compliance with security, privacy, governance, and Responsible AI standards, including HIPAA and enterprise data protection requirements.
• Creates and maintains technical documentation, including solution designs, architecture diagrams, implementation guides, and operational runbooks while sharing knowledge with team members.
• Contributes to Agile or SAFe delivery teams by participating in planning sessions, sprint activities, estimation, and continuous improvement initiatives.
• Evaluates new AI technologies, frameworks, and cloud services and recommends opportunities to improve existing solutions and engineering practices.

• 5+ years of software engineering, machine learning engineering, or AI engineering experience.
• 2+ years of experience building, deploying, or supporting AI/ML or Generative AI solutions in a production environment.
• Experience with cloud platforms such as AWS or GCP, including serverless services, APIs, event-driven architectures, or cloud-native application development.
• Proficiency in Python and experience developing scalable applications using modern software engineering practices.
• Experience with LLMs, prompt engineering, RAG architectures, vector databases, agentic workflows, or equivalent AI technologies.
• Adept at problem solving and decision‑making skills.
• Adept at collaboration and teamwork.
• Adept at growth mindset (agility and developing yourself and others) skills.
• Adept at execution and delivery (planning, delivering, and supporting) skills.

• Hands-on experience with AWS Bedrock, GCP Vertex AI, Azure OpenAI, or similar AI platforms.
• Experience building RAG solutions using vector databases such as Open Search, Pinecone, pgvector, FAISS, or similar technologies.
• Experience developing AI agents using Copilot Studio, Power Automate, Lang Chain, Lang Graph, Llama Index, or similar frameworks.
• Experience developing cloud-native APIs, microservices, and event-driven architectures.
• Knowledge of Responsible AI, model evaluation,…