Data Scientist – Retail Analytics

CVS Health•Wellesley, MA

22h•$86,520 - $173,040

About The Position

The Consumer Engagement & Analytics team at CVS Health is dedicated to improving consumer experience by collaborating with key business areas to deliver impactful analytic products and insights. As a member of the Pricing Analytics team, this role focuses on developing high-visibility products for CVS Retail's strategic priorities. The Data Scientist will utilize data science to optimize pricing decisions, aiming to drive traffic, revenue, and customer satisfaction in the Front Store business. This involves solving complex problems, translating business requirements into testable hypotheses, and building causal inference, econometric, and predictive models to understand localized trends, assess competitive environments, and measure customer impacts. The position also requires developing in-depth knowledge of Retail Merchandising and Pricing processes, working with large datasets, optimizing code, and building scalable, deployment-ready models. A key aspect is staying updated on state-of-the-art modeling methodologies, econometric techniques, and leveraging generative AI to enhance pricing models and explore automation. Cross-functional collaboration with technical and non-technical stakeholders and presenting insights-driven recommendations to leadership are also crucial.

Requirements

1+ years of work experience in retail, consulting, or a related field.
Strong programming skills in Python and SQL.
Proficiency in working with large datasets and distributed computing frameworks.
Hands-on experience with version control (GitLab/GitHub), ML platforms (AWS SageMaker, Databricks, GCP Vertex AI), and familiarity with CI/CD pipelines and MLOps tools (Kubeflow).
Experience with econometric modeling techniques (e.g., price elasticity, promotional lift, cross-effects, hierarchical models).
Experience working with state-of-the-art Deep Learning and NLP models in a non-academic setting.
Excellent communication and presentation skills, attention to detail, and ability to work with multiple stakeholders.

Nice To Haves

3+ years of work experience in retail, consulting, or a related field.
Strong background in pricing and promotion analytics, including elasticity modeling, cannibalization analysis, and competitive price simulation.
Experience with causal inference methods (e.g., difference-in-differences, synthetic controls, propensity score matching).
Familiarity with Bayesian hierarchical modeling and advanced time-series forecasting for retail demand.
Experience managing large-scale projects and working with multiple business stakeholders.
Designed and implemented end-to-end ML solutions, including monitoring and improving model performance in production, experiment tracking, and setting up data drift monitoring systems.

Responsibilities

Solve complex problems, translate business requirements into testable hypotheses and measurable metrics, and build causal inference, econometric, and predictive models to understand localized trends, assess competitive environments, and measure short- and long-term customer impacts to optimize pricing and promotion decisions.
Develop and leverage in-depth knowledge of Retail Merchandising and Pricing processes, translate key drivers of business value into analytics opportunities, and simulate the impact of pricing and promotional decisions to improve customer experience.
Work with large datasets, optimize code, and build scalable, deployment-ready models that work well with CVS Retail’s diverse product portfolio.
Develop robust methodologies and metrics to assess model performance and ensure statistical validity.
Stay up to date on state-of-the-art modeling methodologies, econometric techniques, and latest research in pricing and promotional analytics.
Utilize the latest developments in generative AI (LLMs and other models) to enhance pricing models, rethink deployment readiness and scalability, and explore automation opportunities using AI agents.
Collaborate cross-functionally with technical and non-technical stakeholders, including business partners, engineers, and analytics teams.
Present insights-driven materials with recommendations and go-forward plans to guide internal stakeholders and senior leadership.