Senior/Staff Software Engineer (Behavior Verification)
Posted Updated
- As a Senior/Staff Software Engineer working on driving behavior verification, you are responsible for implementing metrics that evaluate the end-to-end behavior of the Nuro Driver
- These metrics will be used to quantify the safety of the driving behavior in our target ODD
- This requires prior experience with the development or verification of behavior planning/prediction systems for robots, and a collaborative nature to work closely with a variety of teams across Nuro: Systems, Onboard Software, Simulation, Product, and Operations
- Develop and implement in Python generalizable metrics to verify the driving behavior of an autonomous vehicle
- Leverage a combination of machine learning (ML) models and safety metrics from literature to evaluate the end-to-end driving behavior
- Evaluate these metrics on a variety of tests: synthetic and log simulation, on-road logs, closed-course testing data, and third-party accident reconstructions
- Collaborate closely with Systems, Behavior, Perception, Data Science, Product, Legal and Public Trust teams to develop acceptance criteria for metrics and tests
- Partner with simulation infrastructure and test integration teams to set up automated verification workflows
- Generate detailed performance and validation reports to prove that the behavior of the autonomous system is safe to deploy in our target Operation Design Domain (ODD)
Benefits
- Free Caltrain pass and commuter benefits
- Company stock options
- Work from home opportunities
- Health insurance
- 5+ years of technical work experience in a relevant area with 3+ years of experience with software development
- Highly collaborative in nature, with strong abilities to think and communicate analytically and effectively
- Bachelor’s Degree or Master’s Degree in Computer Science, Electrical Engineering, Mechanical Engineering, Robotics, Physics, or related field
- Strong understanding of robotic systems architecture - how sensing, localization, perception, prediction, behavior, and control modules interact
- Hands-on software experience, with the ability to code proficiently in Python or C++
- Familiarity with simulation and real-world testing of autonomous systems
- Background in autonomous vehicles ideally with developing software for L4 autonomous
- Prior experience building computational models for driving behavior or ML based metrics for behavior evaluation