Research and development experience in one or more of the following computer vision/deep learning areas: image/video enhancements, including but not limited to de-noising, de-rain, de-focus, super resolution; human action recognition, video saliency detection, video segmentation, scene understanding; camera/ISP algorithms etc.
Good programming and debugging skills in Python, PyTorch and C/C++
Good written and verbal communication skills in Mandarin and English
Understanding camera sensor, imaging process, digital image signal processing would be a bonus
Experience with real-time system, network compression, network optimization, transfer learning, ML data acquisition and management would be a bonus