内容安全算法工程师-视频理解
Core
Research and development of AI algorithms for content safety in video understanding for products like Douyin and Douyin Volcano.
Role type
Senior IC machine-learning engineer (video understanding, multimodal)
Builds
Content safety features for short video and live streaming products
Domain
Social media, computer vision, NLP, audio analysis
Deliverable
production ML models
Required skills
deep learning, computer vision, natural language processing, speech recognition, image processing, pattern recognition, mathematical modeling
Preferred skills
recommendation systems, OCR, clustering, multi-modal learning, publication in top-tier conferences (NIPS, CVPR, etc.) or competition experience
Technologies
TensorFlow, MxNet, Caffe, C++, Python
Responsibilities
Explore and develop frontier AI deep learning technologies; conduct content analysis including video classification, scene recognition, object detection/tracking, image/audio classification, feature extraction, clustering, OCR, and text modeling; apply these technologies to actual business products.
