The opportunity
Waymo is an autonomous driving technology company with the mission to be the world's most trusted driver. Since its start as the Google Self-Driving Car Project in 2009, Waymo has focused on building the Waymo Driver—The World's Most Experienced Driver™—to improve access to…
What you'll do
Define the approach for quantitative safety risk analysis across sensing and: perception systems engineering, building on top of Waymo-wide risk assessment and management methodologies. You will design, develop, and implement sophisticated quantitative methods and statistical models for evaluating end-to-end performance for current and counterfactual sensor suites.
Apply the defined approach for selected events that occur rarely or have: scarce operational data. The generalized goal is to assess behavioral safety risk across a wide variety of situations like interacting with pedestrian crowds, navigating around floods, and degraded sensing in construction zones.
Develop and prototype novel workflows to:
Analyze to determine the required performance levels of various sensing and perception tasks
Support trade studies to inform architectural decisions for perception hardware or software
Estimate exposure of events relevant to perception-driven behavioral risk
What they're looking for
- Improve quantitative rigor, standardization, efficiency of execution, and: reporting of end-to-end risk from V&V test outcomes in complex contexts.
- Expand existing methodologies that are crucial for breaking into new: operational design domains and addressing emergent challenges
- Collaborate closely with:
- Onboard Software and Evaluation for mapping perception evaluation and planner: evaluation to end-to-end risk in large models
