Software Engineer

About the Company

DiDi's autonomous driving unit was established in 2016 with the mission of developing Level 4 autonomous driving (AD) technology to make transportation safer and more efficient. We believe integrating AD technology into a shared-mobility fleet will generate immense social value.

Responsibilities

• Architect data flow pipelines and APIs for map fusion, real-time map vectorization, and motion planning modules
• Design and deploy software frameworks integrating offline HD maps with online perception data
• Implement and optimize state-of-the-art networks utilizing DETR-style, query-based vector decoding in BEV
• Design, implement, and validate core motion planning algorithms and trajectory optimization
• Own end-to-end deployment pipelines for deep learning mapping models from Python to C++
• Develop real-time map anomaly and scene-change detection algorithms
• Optimize system latency, memory footprint, and multi-threaded execution of C++ modules

Requirements

• B.S./M.S. or Ph.D. in Computer Science, Robotics, Electrical Engineering, or related field
• 3+ years experience for Software Engineer or 5+ years for Senior Software Engineer in autonomous driving or robotics
• Expert proficiency in production-grade C++ (Modern C++14/17/20) and Python prototyping
• Foundational knowledge in path planning (A*, Dijkstra, Hybrid A*, RRT*) and vehicle models
• Deep understanding of robotics fundamentals, coordinate transformations, and spatial geometry
• Strong system design skills with understanding of middleware like ROS2 or DDS

Preferred Qualifications

• Experience with numerical trajectory optimization (MPC, QP, Nonlinear optimization) and solvers (OSQP, Ipopt, Ceres)
• Experience with HD map formats (Lanelet2, OpenDRIVE) and frameworks like MapTR or VectorNet
• Proven track record of deploying deep learning via ONNX and TensorRT into C++ environments
• Knowledge of real-time operating systems (RTOS) and safety-critical software design