Job Responsibilities: Apply cutting-edge machine learning, deep learning, computer vision and other algorithms to implement intelligent robotics business scenarios.

Requirements:

1. Proficient in Python or C++
2. Familiar with at least one image API: OpenGL / OpenCV / Open3D, etc.
3. Familiar with at least one deep learning framework: PyTorch / TensorFlow, etc.
4. Experience with at least one open-source annotation tool: labelme / labelimg / labelstudio, etc. — ability to define data collection standards, annotation specifications, and perform statistical analysis such as data distribution and label distribution.

Familiar with at least one of the following areas:

1. [Image Algorithms] Familiar with at least one domain among object detection, image segmentation, keypoint detection, and object tracking — including basic methods and model architectures. Proficient in data augmentation, model training, result analysis, and structural optimization.
2. [Stereo Vision] Familiar with depth cameras, multi-view geometry, and camera calibration. Experience in depth estimation, 3D reconstruction, and point cloud processing.
3. [Image & Video Processing] Familiar with the basic principles of image processing algorithms and deep learning techniques, including denoising, low-light enhancement, image stabilization, dehazing, and deblurring.
4. [Model Acceleration] Familiar with model compression techniques such as distillation, pruning, quantization, and fixed-point training. Familiar with ONNX / TensorRT frameworks, with deployment experience on Nvidia Jetson / ARM / x86 platforms.

‍