The role involves leading initiatives to measure the quality and trustworthiness of the behavior evaluation portfolio for autonomous driving technology. The individual will identify and drive improvements in evaluation and testing methodologies while partnering with product and engineering teams to build scalable monitoring solutions. Responsibilities include developing roadmaps for key performance indicators and conducting deep dive analyses to address performance bottlenecks. The position requires prototyping improvements in metrics and sampling strategies to ensure evaluation processes remain scientifically rigorous. Additionally, the role entails providing actionable insights for launch criteria and establishing feedback loops to enhance evaluation quality across the organization.

Candidates must possess a degree in a quantitative field such as Statistics, Mathematics, or Physics. The role requires either a PhD with five or more years of industry experience or seven or more years of industry experience in data science. Applicants need a solid statistical background with expertise in experimentation design and causal inference, alongside familiarity with machine learning systems. Proficiency in Python, R, or SQL is required, as is the ability to navigate ambiguous business requirements.