Waymo's Systems Engineering team works together to blend software and hardware systems in groundbreaking new ways. We set the high performance standards that ensure our vehicles run smoothly and keep passengers safe, then design and perform the tests that validate that performance. We're looking for talented teammates who’ll help us maintain strong teamwork and are passionate about driving results.

You will:

• 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 
• 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 
• Test Engineering for cross-calibrating risk from V&V results across various methodologies and coverage competencies, and providing actionable data to improve Waymo’s test tooling across public roads/closed course tests and simulations on logged/synthetic scenarios
• Systems Safety for appropriate allocation of quantitative risk across functional insufficiencies
• Clearly communicate complex quantitative findings and recommendations to diverse stakeholders, including senior leadership, to enable safety at scale. You will collaborate deeply within SysEng and cross-functionally with Product, Simulation, and Data science teams to advance safely and deliver excellence. 

You have:

• Bachelors or higher degree in computer science, math, physics, engineering, or a related field
• 10+ years of engineering experience with demonstrated delivery of high-stakes technical roadmaps that successfully resolved architectural friction and deployed business-critical systems 
• Experience using AI productivity tools for analysis and workflow development 
• Proficiency and experience in:
• Vehicular robotics (development or evaluation) 
• Software development (Python or C++) 
• Statistical or predictive modeling
• Experimental design and developing metrics for quantitative methods
• Deep technical knowledge of at least two of:  
• State of the art ML techniques that power modern perception systems and large end-to-end models
• Quantitative risk estimation using simulators, preferably with sensors-in-loop
• Systems engineering fundamentals such as requirements definition, formal verification and validation methods
• Track record of leading complex projects in safety critical applications with leadership-facing accountability across software, operations, data science, product, and testing
• Excellent verbal and written communication skills, and ability to manage by influence 

We prefer:

• Masters (with thesis) or PhD in machine learning, statistics, robotics, or a related quantitative field 
• Autonomy driving industry experience
• Experience testing on large-scale infrastructure and deploying production-level safety critical systems
• Track record of developing model-driven metrics that influence software or hardware design decisions at scale