感知语义理解算法工程师（J94931）
Core
Develop end-to-end vision-language large models, traffic sign/light recognition, 2D/3D object detection, and scene semantic understanding algorithms for fully autonomous systems.
Role type
Senior IC computer vision and multimodal AI engineer
Builds
Perception and semantic understanding models for autonomous driving/robotics
Domain
Autonomous driving / Robotics / Computer Vision
Deliverable
production ML models
Required skills
C++, Python, Linux development, deep learning (3D/sparse convolution, transformers), mathematical analysis
Preferred skills
LLM/VLM/VLA training experience, publications in CVPR/ICCV/ICRA/IROS/PAMI
Technologies
C++, Python, Linux, 3D convolution, sparse convolution, transformers, LLM, VLM, VLA
Responsibilities
Research and develop vision-language models, traffic sign/light recognition, and object detection algorithms; propose data requirements and build automated data pipelines; collaborate on fully autonomous perception model development.
