北京-计算机视觉算法工程师(J100771)
Core
Research and development of computer vision algorithms including object detection, image segmentation, image generation, and visual understanding, leveraging large models and vision foundation models.
Role type
Computer Vision Algorithm Engineer
Builds
Vision algorithms deployed in actual products
Domain
Computer Vision / Artificial Intelligence
Deliverable
production ML models
Required skills
Deep learning fundamentals, Object detection, Image segmentation, Image generation, Visual understanding, Python, PyTorch, PaddlePaddle, Vision foundation models (SAM, DINO), Transformer architectures (ViT, DETR)
Preferred skills
Publications in CVPR/ECCV/ICCV, Research/competition/project experience in CV
Technologies
PyTorch, PaddlePaddle, ResNet, ViT, DETR, SAM, DINO
Responsibilities
Design training schemes and optimize model performance, Collaborate with multimodal teams to explore vision-language fusion, Track and implement cutting-edge CV research
Seniority
Mid-level IC
