Data Scientist - Assortment Optimization

The Retail Analytics team is helping lead the effort to drive improved consumer experience by partnering with key business areas across CVS Health to deliver impactful analytic solutions and insights. As a member of the Analytics & Behavior Change (A&BC) Merchandising Analytics team, you will be at the forefront of delivering high visibility projects for key strategic priorities. Specifically, you will have the opportunity to drive revenue and customer satisfaction in CVS Health’s Front Store business by using data science to support a product assortment that better fits the needs of our customers.  

In this role, you will have the opportunity to solve complex problems, build predictive models and optimize assortment decisions, working cross-functionally with a range of technical and non-technical stakeholders. We are a fast-paced team focused on building innovative analytics solutions using cloud capabilities. We are looking for individuals who have a keen sense of ownership, accountability, and a desire to deliver high quality work. In this role, you will have the opportunity to:  

• Solve complex problems using operations research, dynamic programming, and reinforcement learning, build and improve optimization models to optimize assortment decisions, 

• Develop and leverage in-depth knowledge of Retail Merchandising business processes, translate key drivers of business value to analytics opportunities, and simulate impact of business decisions to improve customer experience, 

• Guide the technical approach, leverage large datasets, and build scalable and deployment ready models that work well with CVS Retail’s diverse product portfolio, develop robust methodologies to assess model performance, 

• Stay up to date on the state-of-the-art modeling methodologies and latest research, 

• Utilize the latest developments in the generative models (LLMs and other AI models) to improve and enrich the performance of current models, 

• Work cross functionally with a range of technical and non-technical stakeholders including business partners, engineers, and other data and analytics teams. Share progress, findings, recommendations, and their business implications. Present meaningful and insights-driven materials on analytical results with recommendations and go forward planning to guide a variety of audiences including internal stakeholders and senior leadership

• Bachelor’s degree in a quantitative field such as Operations Research/Industrial Engineering, Applied Mathematics, Computer Science, Engineering, or a related field, 

• Strong Python and SQL skills, proficiency in working with large datasets, 

• Familiarity with mathematical optimization models using open-source or commercial optimization solvers (such as Pyomo, Gurobi, Pulp, ILOG CPLEX), 

• Experience working with a data engineering/MLOps team to deploy data science models, familiarity with version control (GitLab or GitHub), and ML platforms (AWS SageMaker, Databricks, GCP Vertex AI, etc.), 

• Excellent communication and presentation skills and attention to detail. Worked in an agile environment, has the flexibility to adapt to changing business needs, 

• Ability to communicate technical concepts to non-technical audiences, including experience creating communication materials (e.g., white paper, slide decks, etc.).