Behavior Planning Software Engineer

Job description

Aurora’s mission is to deliver the benefits of self-driving technology safely, quickly, and broadly.

Develop real-time algorithms for selecting safe and comfortable trajectories for a self-driving vehicle
Integrate motion planning with machine learning to create verifiable AI systems for autonomous driving
Design and implement production-grade software for the Aurora Driver
Design metric suites and testing workflows for rapid iteration on algorithms

BS, MS, or Ph.D. in Robotics, Machine Learning, Applied Mathematics, Computer Science or a related field
4+ years of strong programming and software design skills in Python and/or C++, especially in low latency or real-time environments
Experience in designing, building, and productionizing motion planning algorithms (cost function design, optimization, or sampling-based techniques)
Expertise with GPU or ML toolkits such as PyTorch, CUDA, TensorFlow, JAX, and/or TensorRT
Expertise in machine learning for robotic/agentic applications (reinforcement learning or imitation learning)