• Own end-to-end product experimentation: hypothesis generation, metric definition, experimental design (A/B, multivariate, sequential testing), analysis, and executive-level interpretation. • Design and maintain ML-powered evaluation frameworks for product changes, automation quality, and system reliability (e.g., order accuracy, routing, error rates, conversion). • Build and deploy predictive models, classifiers, and ranking systems that power experimentation, personalization, and product optimization. • Partner with product and engineering to test new features, workflows, and ML models through controlled experiments and incremental rollouts. • Lead offline and online model evaluation, comparing baselines, candidate models, and product variants using rigorous statistical methods. • Use causal inference and quasi-experimental methods when randomized experiments are not feasible. • Develop experiment pipelines and instrumentation: logging, dashboards, monitoring, and automated analysis to ensure measurement integrity. • Perform failure-mode and error analysis to guide product iteration and model improvement. • Translate experiment outcomes into clear product decisions, influencing roadmap prioritization and system design. • Drive experimentation at scale in a fast-moving environment, balancing speed, rigor, and business impact. • Lead and mentor data scientists and analysts, setting standards for experimentation, modeling, and evaluation across the organization.