Senior Software Development 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.

Position Summary

The Senior Software Engineer will design, build, and ship production grade AI powered products and the software and data foundations behind them. You will work with engineering, analysts, data scientists, and product teams in a fast paced, agile environment, using AI/ML and GenAI to reimagine how healthcare is delivered. The role spans the full lifecycle of an AI solution: data pipelines, feature and vector stores, LLM powered backend services and agentic workflows, and user facing applications. You will build these on cloud native, AI ready architectures.

The Senior Software Engineer is expected to have extensive knowledge of modern programming languages and frameworks, and experience designing and developing full stack and data solutions that support machine learning and generative AI use cases at production scale.

Key Responsibilities

• Design, build, and deploy agentic AI systems and LLM powered applications, including multi step workflows, tool use, and orchestration with frameworks such as LangChain and LangGraph
• Develop retrieval augmented generation (RAG) solutions end to end, including ingestion, chunking, embedding generation, vector indexing, retrieval tuning, and grounding of model responses
• Design, build, and maintain the data pipelines, data models, feature stores, and vector stores that feed analytics, ML, and GenAI workloads
• Build full stack applications that expose AI capabilities to users, including responsive front end interfaces (e.g., chat and copilot experiences), backend services, and RESTful/GraphQL APIs
• Integrate applications with LLM APIs, relational databases, data platforms, and vector databases, and optimize data access patterns, latency, and token/inference cost
• Implement MLOps/LLMOps practices, including model and prompt versioning, evaluation pipelines, monitoring for quality, drift, and hallucination, and automated release workflows
• Implement CI/CD pipelines, automated testing (including AI evaluation and regression testing), infrastructure as code, and observability across applications, data pipelines, and AI services
• Troubleshoot and resolve production issues across the stack, from data quality and model behavior to API performance and UI experience
• Apply AI assisted development tools to improve engineering productivity, code quality, and delivery speed, and help establish team standards for their use
• Participate in design and code reviews, mentor junior engineers, and champion engineering and AI best practices
• Partner with product owners, designers, analysts, and data scientists to translate business needs into AI enabled technical solutions
• Ensure solutions meet security, privacy, and compliance standards (e.g., HIPAA), and apply responsible AI practices including guardrails, PHI/PII protection, auditability, and human in the loop controls

Required Qualifications

• 6+ years of professional software engineering experience, with strong experience building full stack applications and a track record of delivering AI/ML enabled solutions to production
• Proficiency in at least one modern backend language (e.g., Python, Java, Node.js/TypeScript) and one modern front end framework (e.g., React, Angular, Vue)
• Hands on experience building and deploying Agentic AI solutions in complex cloud infrastructure environments, including orchestration frameworks (e.g., LangChain, LangGraph) and integration with LLM APIs
• Experience building data pipelines to support ML/AI workloads, including feature engineering, embedding generation, and integration with vector databases (e.g., Pinecone, Weaviate, pgvector) for RAG use cases
• Experience designing and building RESTful APIs and microservices, including authentication/authorization, API security, and service to service integration, with experience serving AI/LLM capabilities through APIs
• 6+ years of experience working with SQL and relational database management systems, including schema design and query optimization
• 3+ years of experience with cloud platforms and data engineering platforms such as AWS, GCP, Azure, Databricks, or Snowflake
• Familiarity with MLOps/LLMOps practices, model versioning, monitoring, and pipeline support for production ML/AI systems (e.g., Vertex AI, SageMaker, Azure ML)
• Experience with CI/CD, containerization (Docker, Kubernetes), Git based workflows, and automated testing practices
• Hands on experience troubleshooting data, application, and AI system issues
• Hands on experience with performance improvement techniques across data, backend, front end, and AI inference layers

…