Drimva

Waymo

Sr. Staff Systems Engineer, Perception-Planner Risk

$272K–$336K

Mountain View, CA, US +1 · Senior Staff · Full-time · Posted Oct 30, 2026

Location
Mountain View, CA, US
Mountain View, California, United States
Experience
10+ years of engineering experience.
Education
Bachelor’s or higher degree in computer science, math, physics, engineering, or a related field.

About the job

Defines quantitative methods to assess perception-related safety risk in autonomous vehicles and uses those methods to guide system design, testing, and operational decisions.

What you'll do

  • Develop statistical models and workflows to evaluate end-to-end risk across current and counterfactual sensor suites.
  • Apply risk analysis to rare events and support perception hardware/software trade studies and performance requirements.
  • Collaborate across engineering and safety teams, communicate findings, and improve risk assessment from verification and validation results.

What they ask for

  • Bachelor’s or higher degree in computer science, math, physics, engineering, or a related field.
  • 10+ years of engineering experience delivering high-stakes technical roadmaps and business-critical systems.
  • Experience using AI productivity tools for analysis and workflow development.
  • Proficiency in vehicular robotics, Python or C++ software development, statistical or predictive modeling, and experimental design; deep technical knowledge of at least two specified areas: modern perception ML, quantitative risk estimation using simulators, or systems engineering.

Nice to have

  • Master’s with thesis or PhD in machine learning, statistics, robotics, or a related quantitative field.
  • Autonomy driving industry experience, large-scale infrastructure testing, or production safety-critical system deployment.

Pay

$272,000—$336,000 USD base salary

Tools

Python, C++, ML, simulators, sensors-in-loop

AI focus

Uses AI productivity tools for analysis and workflow development; assesses risk for perception systems, including modern ML techniques and large end-to-end models.

Model-written summary · the original posting is authoritative

First seen Oct 31, 2026 · Last verified Nov 5, 2026 (UTC)