Description
Rigorous performance evaluation of the Waymo Driver is a critical part of scaling our ride hailing service and achieving Waymo’s audacious goals. Waymo data scientists work hand-in-hand with engineering teams at each stage of the software development cycle, employing statistical models and developing metrics and measurement frameworks to ensure that the Waymo Driver meets our strict standards for safety, compliance, and driving and service quality. Autonomous driving presents a new paradigm in data science: in addition to leveraging data collected on-road, we generate our own data using state-of-the-art simulation technology—resulting in denser signals and challenging new problems in estimation and experimental design.
In this hybrid role you will report to a data science manager.
You will:
- Develop evaluation frameworks for autonomous vehicle performance, for large-scale ML models, and for the quality of simulation.
- Develop new metrics, interpret trends, and investigate anomalies in data from simulation and on-road driving.
- Develop novel statistical methods to handle unique aspects of AV data; e.g. rate estimation with rare events, combining real and synthetic data, etc.
- Frame and solve ambiguous problems by scoping technical priorities and innovating on statistical methods.
- Derive data-driven conclusions and communicate findings to senior stakeholders.
- Establish yourself as the point-of-contact for a significant project area by using data to drive technical decisions and demonstrate success.
- Collaborate with Product and Engineering partners developing the Waymo Driver and Waymo’s simulation software; facilitate deployment readiness decisions for both products.
- Mentor other data scientists and provide constructive technical feedback within the team and across Waymo.