Data Scientist II - Experimentation

At Chewy, it is our mission to become the most trusted and convenient online destination for pet parents and our partners – vets and service providers – alike.  Our success is measured by the happiness of the people and pets we serve, not simply by the amount of pet supplies we deliver. That’s why we continue to think of outside-the-Chewy-box ways to delight, surprise, and thank our loyal pet lovers!

Our Opportunity:

Chewy is looking for a Data Scientist II to join the Experimentation Platform (A/B testing). Our platform supports 100+ active internal users across multiple teams and organizations, enabling rigorous A/B testing to drive new customer experiences. In this role, you’ll be instrumental in establishing an experimentation culture founded on core principles of statistical rigor and effective methodology design. This is a high-impact, high-visibility position that plays a critical role in how Chewy measures and implements customer-facing changes. You'll work cross-functionally with teams across the business, gaining exposure to diverse domains and influencing decision-making at the highest levels. Join a collaborative, fast-paced team where you'll tackle new challenges daily, contribute to meaningful outcomes, and grow alongside a platform that’s central to Chewy’s core business strategy. 

 What You'll Do: 

• Employ statistical methods to address common pitfalls like peeking, multiple comparisons, p-hacking. 
• Apply statistical methodologies to design and analyze online experiments (e.g., A/B/n tests, holdouts). 
• Help develop and maintain diagnostic systems for experiment quality (e.g., bias detection, data quality alerts, Session Ratio Mismatch). 
• Develop relevant surrogate metrics for faster and more accurate experimentation considering full customer journey and tradeoffs.  
• Build out and operationalize causal inference models to calculate annualized incremental lift on output metrics such as revenue. Create models to measure long-term impact using high value actions. 
• Support experimentation platform users with guidance on test setup, metric selection, and hypothesis framing. 
• Ensure quality of data and computation by developing monitoring and alerting mechanisms to catch spillovers and bias and provide guidance on step-wise identification of root-causes. 
• Define and operationalize experimentation best practices, statistical and scientific methodologies and scalable frameworks for creating, monitoring, and learning from experiments. 
• Build AI agents to help optimize experiment workflows and knowledge retrieval.

What You’ll Need: 

• Bachelor’s degree in a quantitative field (e.g., Statistics, Mathematics, Data Science, Economics, Computer Science) or related experience.  
• 3+ years Data Science experience. 
• 3+ years of experience with A/B testing, preferably within an e-commerce environment. 
• 3+ years of experience with causal inference techniques or modeling long-term treatment effects (Diff-in-diff, Propensity Score Matching, Causal Forest, etc...). 
• Strong foundational knowledge in statistics (e.g., hypothesis testing, confidence intervals, variance reduction). 
• Advanced object-oriented programing in Python.  
• Advanced knowledge of SQL.  
• Experience communicating insights to non-technical audiences. 
• Familiarity with using LLMs and AI Agents to automate data and analytical workflows.