Software Engineer – Map Fusion & Planning

About this role

DiDi Autonomous Driving seeks a Software Engineer to develop map fusion and motion planning systems for Level 4 autonomous vehicles. You'll integrate HD maps with real-time perception data, implement advanced neural networks for vector-based mapping, and design trajectory optimization algorithms that safely navigate complex environments.

What you'll do

• Design data pipelines and APIs for map fusion, vectorization, and behavior planning modules
• Integrate offline HD maps with online perception to create unified local environment models
• Implement DETR-style neural networks for bird's-eye-view map element generation
• Develop and validate motion planning algorithms with tight feedback loops between mapping and trajectory optimization
• Own end-to-end deployment of deep learning models from Python training to C++ runtime execution
• Build anomaly detection and scene-change algorithms for planning reliability under map uncertainty

What they're looking for

• C++ and Python programming
• Deep learning frameworks and ONNX optimization
• Motion planning and trajectory optimization
• Autonomous driving systems architecture
• Real-time embedded software optimization
• DETR-style neural networks and computer vision
• Multi-threaded and GPU-accelerated computing
• Robotics or spatial computing experience