Senior Data Scientist, Customer Analytics & Personalization

Senior Data Scientist, Customer Analytics & Personalization

Framingham, MA, United States (On-site)

Staples is seeking a Senior Data Scientist I with 7+ years of progressively complex experience to lead high-impact work in customer segmentation, personalization, experimentation, and omnichannel measurement, including multi-touch attribution (MTA).

This role sits at the intersection of data science, analytics engineering, and applied machine learning, and plays a critical role in shaping how Staples engages customers across digital, in-store, and hybrid (BOPIS / delivery) journeys. You will partner closely with Product, Marketing, Merchandising, and Engineering to drive measurable customer and revenue impact.

• Design and maintain customer segmentation frameworks using large-scale transactional, behavioral, and engagement data.
• Develop segmentation strategies based on lifecycle stage, purchase frequency, basket composition, category affinity, promotion responsiveness, and channel preference.
• Build and deploy personalization and targeting models (e.g., propensity, uplift, ranking) to improve engagement, conversion, and retention across marketing and customer touchpoints.
• Translate analytical and model outputs into actionable decisioning logic.
• Design, analyze, and interpret experiments and quasi-experiments across marketing, merchandising, and customer engagement use cases.
• Apply causal inference techniques such as A/B testing, difference-in-differences, matching, uplift modeling, and other incrementality approaches.
• Support experiments conducted at multiple levels, including customer-, geo-, and store-level designs, while accounting for seasonality, spillover effects, and operational constraints.
• Partner with stakeholders to ensure tests are well-powered, statistically sound, and aligned with business objectives.

• Build and evolve omnichannel measurement frameworks, including multi-touch attribution and incrementality models, to assess the impact of customer and marketing touchpoints.
• Measure the effectiveness of digital and offline channels, such as paid media, email, loyalty programs, promotions, and in-store activity.
• Clearly communicate model assumptions, limitations, and tradeoffs to technical and non-technical audiences to support decision-making.
• Collaborate with Analytics and Data Engineering teams to define clean, reliable, and scalable data models at the SKU, transaction, store, and customer level.
• Productionize analytical models and data products using best practices for code quality, versioning, validation, monitoring, and retraining.
• Write maintainable, well-documented code and contribute to shared data science tooling and standards.

• Act as a senior individual contributor and technical leader, setting a high bar for analytical rigor and statistical judgment.
• Review and provide feedback on analyses and models developed by other data scientists.
• Proactively identify opportunities where data science can improve customer experience, marketing efficiency, and commercial outcomes.
• Influence strategy with data-driven insights.

• Required Qualifications
• 7+ years experience in Data Science, Analytics Engineering, ML Engineering, or related roles.
• Strong foundation in statistics, probability, experimental design, and causal inference.
• Demonstrated experience with customer analytics, including segmentation, personalization, or marketing measurement.
• Hands-on experience designing and analyzing experiments and observational studies in real-world business settings.
• Proficiency in Python and SQL.
• Experience deploying models into production.
• Ability to communicate complex technical concepts clearly to non-technical stakeholders.

• Experience in retail, e-commerce, or consumer-facing businesses.
• Experience building or evaluating multi-touch attribution, incrementality, or media measurement models.
• Familiarity with uplift modeling or treatment effect estimation.
• Experience working with modern data stacks (e.g., cloud data warehouses, dbt, feature stores).
• Exposure to ML systems, model monitoring, or…