CVS Health is a company focused on building a more connected and compassionate health experience. They are seeking a Staff Software Engineer Lead to develop scalable software systems that leverage AI-driven capabilities and emerging technologies to enhance patient outcomes and streamline healthcare delivery.
Responsibilities:
- Lead the development of scalable software systems that integrate generative AI models, autonomous agents, and machine learning pipelines
- Collaborate with cross-functional teams to identify opportunities for AI-first innovation across digital health products
- Drive the adoption of AI engineering best practices, including prompt engineering, model fine-tuning, and responsible AI governance
- Facilitate technical discussions between Application Architects and developers to ensure AI capabilities are embedded into the design and architecture of new solutions
- Stay current with advancements in AI and emerging technologies, and translate them into actionable strategies for product development
- Design, develop, and maintain scalable data pipelines and APIs using Python and FastAPI
- Integrate and orchestrate LangChain and LLM-based services into production environments
- Build robust data preprocessing workflows for structured and unstructured data
- Develop and maintain integrations with external and internal RESTful services
- Collaborate with ML engineers, data scientists, and product teams to deliver end-to-end AI solutions
- Implement DevOps best practices including CI/CD pipelines, containerization (Docker)
- Identify and resolve security vulnerabilities in data services and APIs
- Monitor and optimize system performance, reliability, and scalability
Requirements:
- 5+ years of experience in software/data engineering with a focus on backend development
- Strong proficiency in Python and experience with FastAPI for building APIs
- Hands-on experience with LangChain, LLMs (e.g., OpenAI, Vertex AI, Hugging Face Transformers), and vector databases
- Solid understanding of REST API design and integration
- Experience with data preprocessing, ETL/ELT pipelines, and working with large datasets
- Familiarity with DevOps tools such as Docker, Kubernetes, GitHub Actions, Jenkins, etc
- 3+ years Experience with cloud platforms (AWS, GCP, or Azure)
- Strong understanding of application security, including authentication, authorization, and vulnerability mitigation
- 3+ years coding in Python/PySpark, Java Springboot, NoSQL, SQL, and LLM modeling
- Experience with streaming data frameworks (e.g., Kafka, Spark Streaming)
- Familiarity with data governance and compliance standards (e.g., PHI, PII, HIPAA)
- Contributions to open-source projects in the AI/ML or data engineering space
- Experience with Prompt Engineering developing solutions leveraging LLM models
- 3+ years coding in Python/PySpark, SQL, and LLM modeling
- 3+ years in cloud-based platforms such as Azure, GCP and AWS