The Vehicle Interaction team tackles critical autonomous driving challenges, directly responsible for modeling agent interactions with other vehicles to advance our mission of safety and building the world's most trusted driver. The team develops agent reasoning and motion planning algorithms to resolve complex interactive scenarios—including lane changes, merges, unprotected maneuvers, and cut-ins. By combining core robotics principles with scalable, production-deployed machine learning models, the team enables the Driver to safely, predictably, and seamlessly navigate dynamic real-world environments.

In this hybrid role, you will report directly to the Technical Lead Manager.

You will:

• Design, evaluate, and deploy learned interaction policies to handle complex navigation and yielding scenarios.
• Collaborate cross-functionally at the intersection of prediction and planning, leveraging large-scale models to solve complex agent interaction problems.
• Integrate learned models into closed-loop simulation environments, benchmark against rigorous safety metrics, and drive seamless transitions to production releases.
• Focus on high-impact product outcomes, making pragmatic engineering decisions to accelerate the shift from rule-based heuristics to scalable, data-driven policies.

You have:

• BS in Computer Science, Machine Learning, Robotics, a related technical field, or equivalent practical experience.
• 5+ years of software engineering experience developing high-performance, efficient C++ code.
• Hands-on experience building ML models, including expertise in learned driving policies (RL/imitation learning), PyTorch or JAX, closed-loop simulation evaluation, and a proven track record of shipping models to production.
• Proven capability to collaborate effectively across cross-functional engineering teams.

We prefer:

• MS or PhD in Computer Science, Machine Learning, Robotics, or a related technical field.
• Demonstrated software engineering expertise in motion planning or related autonomous systems problems.
• Experience building, training, and benchmarking machine learning systems at scale.
• Technical leadership experience guiding engineers or leading small project teams.