Research Scientist, Model Evaluation

Job description

办公地点

北京，芜湖 ，上海，可任选其一。

• Establish a comprehensive AI model evaluation framework and standards
• Develop automated evaluation tools and platforms
• Own model performance, safety, and reliability assessment
• Drive evaluation results to inform model optimization and iteration" "
• 3+ years in computer vision research; deep expertise in object detection, semantic segmentation, multi-object tracking
• Led large-scale auto-labeling system R&D successfully deployed in autonomous driving projects
• Proficient in weakly-supervised, semi-supervised, and self-supervised learning for annotation tasks
• Strong algorithm engineering skills and data production efficiency optimization experience"