Autonomy Planning Engineer - Trajectory & Decision-Making

Didi Labs; San Jose (CA); On-site; USD 141,000 - 282,000; Full time

Job summary

DiDi Autonomous Driving in San Jose, CA seeks a Software Engineer / Senior Software Engineer to contribute to the core planner engine for decision-making, trajectory generation, and evaluation.

You will apply both classic robotics planning and machine learning methods to deliver safe, comfortable trajectories for autonomous vehicles, collaborating with Perception, Prediction, Motion Control, and Safety teams to refine evaluation metrics and validation of planning behavior.

Qualifications

• Bachelor’s or higher degree in Computer Science, Robotics, Electrical Engineering, Applied Mathematics, or a closely related technical field.
• 2–5+ years of software engineering experience writing production-grade C++ in autonomous driving, robotics, or complex real-time systems.
• Strong understanding of behavior planning, decision-making, and trajectory generation algorithms.
• Solid understanding of probability, statistics, and machine learning fundamentals.

Responsibilities

• Design, implement, and maintain high-performance, production-grade C++ software for trajectory candidate generation and scoring.
• Apply probabilistic, statistical, and machine learning methods to assess dynamic trajectory risk and evaluate trajectories under uncertainty.
• Profile, optimize, and test online planning software for low-latency execution on embedded platforms.
• Collaborate with Perception, Prediction, Motion Control, and Safety teams to refine metrics and validate planning behavior.

Skills

Machine learning basics

Probability & statistics

Trajectory planning

Problem solving

Education

Bachelor’s or higher in CS/Robotics/EE/Applied Math

Tools

C++

Embedded platforms

Job description

DiDi Autonomous Driving in San Jose, CA seeks a Software Engineer / Senior Software Engineer to contribute to the core planner engine for decision-making, trajectory generation, and evaluation.

You will apply both classic robotics planning and machine learning methods to deliver safe, comfortable trajectories for autonomous vehicles, collaborating with Perception, Prediction, Motion Control, and Safety teams to refine evaluation metrics and validation of planning behavior.