This role combines the rigor of experimentation with the creativity of detective work. You'll design A/B tests that measure product impact, build dashboards that reveal how our AI models perform across different user segments, and investigate thorny questions like "What makes a good AI-generated presentation?" or "Why did this feature work differently for enterprise versus consumer users?" You'll partner closely with product, engineering, and design teams to define quality metrics, uncover edge cases, and guide decisions with data.