岗位描述
岗位职责
"• Lead R&D and optimization of large-scale computer vision models
• Develop multi-modal perception algorithms powering intelligent driving vision systems
• Drive application of vision models in vehicle detection, scene understanding, and beyond
• Build efficient visual data processing and annotation pipelines"
岗位要求
"• 5+ years in computer vision research; expert in training and optimizing large-scale vision models
• Deep expertise in visual perception, 3D reconstruction, and multi-modal learning; autonomous driving experience is a plus
• Able to independently lead a vision model from research through edge deployment
• Strong engineering skills — proficient in model compression and acceleration techniques"