Aurora Innovation
Behavior Planning Software Engineer
$139K–$223K
Mountain View, CA +1 · Hybrid · Full-time · Posted Aug 4, 2026
- Location
- Mountain View, CA
San Francisco, CA - Experience
- 4+ years; no alternatives stated.
- Education
- BS, MS, or Ph.D. in Robotics, Machine Learning, Applied Mathematics, Computer Science, or a related field.
About the job
Develops real-time behavior-planning software and algorithms that select safe, comfortable trajectories for self-driving vehicles.
What you'll do
- Develop real-time trajectory-selection algorithms and 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 metrics and testing workflows to support rapid algorithm iteration.
What they ask for
- BS, MS, or Ph.D. in Robotics, Machine Learning, Applied Mathematics, Computer Science, or a related field.
- 4+ years of programming and software design experience in Python and/or C++, especially in low-latency or real-time environments.
- Experience designing, building, and productionizing motion-planning algorithms, including cost-function design, optimization, or sampling-based techniques.
Nice to have
- Expertise with GPU or ML toolkits such as PyTorch, CUDA, TensorFlow, JAX, and/or TensorRT.
- Expertise in machine learning for robotic/agentic applications, such as reinforcement learning or imitation learning.
Pay
$139,000 - $223,000 per year (base salary)
Tools
Python, C++, PyTorch, CUDA, TensorFlow, JAX, TensorRT
AI focus
Integrates motion planning with machine learning to create verifiable AI systems for autonomous driving; the role develops trajectory-selection algorithms for self-driving vehicles.
Model-written summary · the original posting is authoritative