Bring your heart to CVS Health. Every one of us at CVS Health shares a single, clear purpose: Bringing our heart to every moment of your health. This purpose guides our commitment to deliver enhanced human-centric health care for a rapidly changing world. Anchored in our brand - with heart at its center - our purpose sends a personal message that how we deliver our services is just as important as what we deliver.

Our Heart At Work Behaviors™ support this purpose. We want everyone who works at CVS Health to feel empowered by the role they play in transforming our culture and accelerating our ability to innovate and deliver solutions to make health care more personal, convenient and affordable.

Position Summary:

We are seeking an innovative and highly skilled Lead Data Scientist to join our Medicare Member Experience Data Science Insights Team. In this role, you will drive the development of cutting-edge ML to improve the experience of millions of members. Techniques including hierarchical multi-label classification, unstructured data analysis and modeling over call and text documents, and grounded sequence models (where appropriate) will be utilized to create an application to trend member feedback. Using the outputs of the modeling process, your contributions will identify key topics for improving member experience, enabling business stakeholders to leverage BI outcomes and enhance member outcomes.

• Developing and deploying machine learning models in both on-premises and cloud environments.
• Using Python with machine learning libraries such as TensorFlow, scikit-learn, or PyTorch.
• Applying NLP techniques to unstructured data, including surveys, complaints, and transcripts.
• Cloud platforms (GCP, AWS, or Azure), with experience using cloud-native tools for data processing and model deployment.
• Experience with NLP techniques, such as sentiment analysis, topic modeling, and transfer learning, especially using transformer-based models.
• Using SQL to aggregate, filter, and group data for analysis.
• Version control systems (e.g., Git) to manage code and collaborate effectively with teams.
• Familiarity with the software development life cycle including developing, testing, and deploying changes to end-users.
• Demonstrated experience with Agile frameworks like Scrum, SAFe, Kanban, or Lean.
• Experience with project management tools like Jira, Trello, or Azure DevOps, and a track record of delivering projects on time.
• Familiarity with Python IDEs and a basic understanding of programming tools such as formatters, linters, and test suites.
• Communicating technical concepts to both technical and non-technical stakeholders.

• Certification with Google Cloud Platform (GCP) is highly preferred, or extensive experience with GCP Managed Services (BigQuery, VertexAI, DataProc, DataFlow, and/or Google Kubernetes Engine).
• Experience using DataFlow (Apache Beam) for data processing (or DataProc / Spark).
• Use of Single Program Multiple Data (SPMD) Parallelism and/or TPUs, particularly with JAX
• Knowledge of the post-training ML lifecycle, including model monitoring, analysis, retraining, and bias evaluation
• Experience with embedding visualization for LLMOps and comfort using visualization tools (potentially for Dash Enterprise).
• Experience managing the ML lifecycle through MLOps best practices, including monitoring, retraining, and model bias evaluation.
• Ability to mentor junior data scientists and drive cross-functional data science projects.
• Familiarity with customer experience data, particularly within healthcare or Medicare programs.
• Knowledge of Python IDEs and a basic understanding of programming tools such as formatters, linters, and test suites.

• Bachelor's degree in a quantitative discipline, or equivalent relevant experience (required).
• Master's degree in a quantitative field (preferred).