Senior Data Scientist

OverviewThis Senior Data Scientist will drive causal and machine learning-based analyses to measure the impact of product features on user behavior, engagement, and business outcomes, translating results into clear, actionable recommendations. The role partners closely with product, analytics engineering, and fellow data scientists to build in-house causal inference tools, define KPIs, build production-ready analytical workflows, and deliver high-quality, governed visualizations. Success in this role requires strong statistical judgment, experience with product-driven ML, and a focus on delivering insights that are both trustworthy and immediately usable by cross-functional stakeholdersKey ResponsibilitiesCausal InferenceDesign, implement, and productionalize statistically rigorous causal analyses to quantify the impact of product features on user behaviors, engagement metrics, and downstream business outcomesDevelop and maintain causal frameworks that link product interventions to behavioral change, engagement shifts, and business performanceSelect and apply appropriate experimental and observational methods, leveraging regression- and ML-based approaches where appropriate to control for confounding and heterogeneityValidate causal findings through robustness checks, sensitivity analyses, and clear articulation of assumptions and limitationsTranslate results into clear, actionable recommendations that inform product strategy, marketing decisions, and executive-level prioritizationDevelop analytical notebooks and workflows that are reproducible, scalable, and suitable for deployment in production environmentsKPI DevelopmentPartner with product and cross-functional stakeholders to define feature-level engagement and efficacy KPIs aligned with business objectivesIncorporate model-derived signals (e.g., predicted engagement, risk scores, uplift estimates) into KPI frameworks where appropriate to improve measurement and decision-makingImplement testing, documentation, and versioning practices to ensure KPI definitions are reliable, discoverable, and consistently interpretedMaintain metric documentation and metadata to support self-service analytics and cross-functional consumptionData VisualizationDesign and deliver high-quality visualizations in Looker and Databricks that clearly communicate analytical and ML-driven insights without requiring supplemental explanationEnsure visual outputs are intuitive, decision-oriented, and aligned with established data visualization best practicesIncorporate generative AI capabilities into visualization and analytics assets where appropriate to improve interpretability and cross-functional adoptionSupport visualization governance by implementing CI/CD workflows, validation checks, and approval processes to ensure production dashboards meet quality and consistency standards prior to releaseQualificationsStrong statistical experience in causal inference methods like Difference in Difference, propensity score matching, regression discontinuity analysis, and randomized control trials to help link product changes to business outcomesApplied experience building and evaluating machine learning models for prediction, segmentation, or uplift in a product or business contextAbility to develop reproducible, scalable analytical notebooks and workflows that transition effectively from development to production environmentsExperience partnering with product teams to define feature-level KPIs and building robust, well-documented dbt models to expose those metrics across analytics layersStrong track record of creating clear, decision-oriented visualizations in tools such as Looker and Databricks that communicate insights unambiguously to cross-functional stakeholders3-5+ years of experienceTools and libraries: dbt, databricks, statsmodels, scipy, scikit-learn, causalml, prophetLanguages: sql, python, r At Tonal, we believe that the unique and varied lived experiences of our teammates contribute to our overall ... (truncated, view full listing at source)