Senior Research Engineer, Collision Avoidance Modeling

Nuro•Mountain View, CA

About The Position

As a Senior Research Engineer, Collision Avoidance Modeling on the Systems Engineering team, you will work closely with the autonomy software, operations, simulation, and data platform teams to validate autonomy performance. You will be responsible for assessing conflict scenarios by architecting and developing tooling which quantifies collision risk. You will be responsible for identifying through analysis and testing any collision-related risks resulting from functional insufficiency. You will ensure that these risks are managed and tested appropriately, driving software architecture and development, engineering roadmaps, validation, on-road operations, and the safety case.

Requirements

5+ years of technical work experience in a relevant area, of which 3+ years should be in robotics software research and development (offboard or onboard).
Experience with both simulation and on-road testing of autonomous vehicles using well-defined metrics to score good driving behavior, with strong algorithmic problem solving skills and Python experience.
Highly collaborative in nature with strong abilities to think and communicate analytically and effectively, both verbal and written.
Self-starter and fast learner - you should be passionate about picking up new skills and approaching unstructured problems from first principles while prioritizing and managing workload to meet critical project deadlines.

Nice To Haves

Experience with naturalistic driving data involving collisions and collision avoidance.
Familiarity with STPA, ISO 21448, and ISO 8800.
Experience working with real-world datasets (e.g. NuScenes) and simulators (e.g. Carla).

Responsibilities

Design, develop, and maintain methods and software which evaluates collision risk in the context of conflict scenarios in on-road logs or in simulation by modeling both crash dynamics and predictive behavior of agents.
Develop labeling processes and simulation software for the extraction of parameters from logged conflict scenarios.
Leverage scientific literature and real-world data from public roads and closed course/track to model evasive maneuver responses and collision severity.
Evaluate, track, and report collision risk, making strategic recommendations based on the results for test realism improvements, changes to autonomy architecture, and mitigations.
Communicate effectively in a cross-functional product development team and present risks and requirements effectively.