DiDi Labs
Software Engineer – Map Fusion & Planning
About this role
DiDi Autonomous Driving seeks a Software Engineer to design and deploy map fusion and motion planning systems for Level 4 autonomous vehicles. You'll integrate HD maps with real-time perception, implement advanced neural networks for vectorized mapping, and optimize safety-critical planning algorithms for production deployment.
What you'll do
- Architect data pipelines and APIs for map fusion, vectorization, and motion planning modules
- Design frameworks integrating offline HD maps with online perception into unified environment models
- Implement and optimize DETR-style vector decoding networks in bird's-eye-view for map generation
- Develop and validate core motion planning algorithms with tight feedback loops for trajectory optimization
- Own end-to-end deployment of deep learning models from Python training through C++ runtime execution
- Build real-time map anomaly detection and performance optimization for safety-critical systems
What they're looking for
- C++ and Python programming
- Autonomous driving or robotics architecture
- Deep learning frameworks and model optimization (ONNX)
- Motion planning and trajectory optimization
- Real-time systems and performance optimization
- Geometric algorithms and spatial computing
- GPU/CPU optimization and multi-threading
- Sensor perception integration
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
DiDi Labs
DiDi Labs develops autonomous driving technology for Level 4 vehicles, focusing on motion planning, behavioral decision-making, map fusion, and robotic simulation systems. The company is hiring software engineers and researchers to build algorithms, trajectory optimization systems, and cloud-based simulation infrastructure that enable safe and intelligent autonomous vehicle navigation.
View all jobs at DiDi LabsLikely interview questions
- Describe your experience integrating HD maps with real-time sensor data in autonomous systems.
- How have you optimized deep learning model deployment from Python to production C++ runtime?