As a Senior Data Scientist on the CX Consumer Analytics team, you will serve as the foundational link between CX operations and top-line financial impact, owning the revenue calibration models, experimentation frameworks, and behavioral intelligence that connect every customer support interaction to Coinbase's asset accumulation flywheel. You will partner closely with CX Analytics Engineers, Program Managers, and Product teams to translate complex operational and behavioral data into defensible, executive-ready insights that drive measurable improvements in retention, product adoption, and automation quality.

What you'll do:

• Own and evolve CX's Downstream Impact of Support (DSI) revenue calibration models, translating support interaction data into quantified revenue signals.
• Design and execute causal inference frameworks and experiments to measure the incremental impact of CX programs (Concierge, Proactive Outreach, automation interventions) on customer retention and product engagement.
• Build and maintain LLM-powered classification pipelines for CX contact taxonomy, customer friction detection, and issue attribution, partnering with Analytics Engineers to productionize models into CX's governed Source of Truth infrastructure.
• Partner with CX Program Managers and Product teams to define segmentation models and behavioral signals that enable personalized experiences and improve business outcomes.
• Maintain a high bar for statistical rigor across CX's analytics function, ensuring experimentation, causal analyses, and model outputs meet the standards required for executive reporting and regulatory defensibility.

Required Skills and Experience:

• A BA/BS in a quantitative field (e.g., Statistics, Mathematics, Computer Science, Economics) with 5+ years of relevant experience, or a PhD in a quantitative field with 3+ years of relevant experience.
• Demonstrated experience building revenue attribution or causal impact models and driving data science projects through ambiguous problem spaces in a consumer-facing or operational analytics context.
• Practical expertise applying statistical concepts including A/B testing, causal inference, and ML to real-world business problems, with a high bar for production-grade accuracy and evaluation rigor.
• Experience designing and deploying LLM-based classification or NLP pipelines for operational or customer-facing use cases.
• Ability to influence cross-functional stakeholders by synthesizing complex model outputs into clear, actionable narratives for executive and product audiences.
• Demonstrates the ability to responsibly use generative AI tools and copilots (e.g., LibreChat, Gemini, Glean) in daily workflows, continuously learn as tools evolve, and apply human‑in‑the‑loop practices to deliver business‑ready outputs and drive measurable improvements in efficiency, cost, and quality.