Senior Software Engineer, Motion & Behavioral Planning

Didi Labs; San Jose (CA); Hybrid; USD 129,000 - 215,000; Full time

Job summary

DiDi Labs in San Jose, CA seeks a Software Engineer or Sr. Software Engineer to build core decision‑making and motion planning for autonomous vehicles.

You will implement algorithms that enable safe, smooth navigation in complex environments, spanning high-level behavior to low-level trajectory optimization. You will design the behavioral planner, optimize motion planning, and work with geometry and velocity systems to produce geometrically feasible and comfortable paths.

Qualifications

• B.S./M.S. in computer science, robotics or a related field.
• Experience in autonomous systems or automotive software development.
• Strong proficiency in C++ and Python for real-time algorithms.
• Knowledge of decision-making, motion planning, and trajectory ranking concepts.

Responsibilities

• Design and implement the coreBehavioral Planning logic for high-level actions.
• Develop motion planning algorithms integrating geometry reasoning and velocity reasoning into trajectories.
• Architect and enhance geometry systems for feasible paths.
• Architect and refine velocity systems for safe, comfortable profiles.
• Model driving scenarios and world interactions for the planner.
• Collaborate with Prediction, Perception, and Control teams for end-to-end flow.
• Analyze, test, and debug system performance across scenarios.

Skills

C++

Python

Robotics fundamentals

Real-time algorithms

Education

B.S./M.S. in Computer Science or Robotics

Tools

Real-time systems

Geometric reasoning

Job description

DiDi Labs in San Jose, CA seeks a Software Engineer or Sr. Software Engineer to build core decision‑making and motion planning for autonomous vehicles.

You will implement algorithms that enable safe, smooth navigation in complex environments, spanning high-level behavior to low-level trajectory optimization. You will design the behavioral planner, optimize motion planning, and work with geometry and velocity systems to produce geometrically feasible and comfortable paths.