Responsibilities
Team Introduction: The Douyin Recommendation Technology Team is responsible for the full-stack optimization of the recommendation page with the highest usage time of Douyin. The underlying model also supports other important business scenarios of Douyin. Our work involves the optimization of large-scale recommendation algorithms, the solution of optimization problems with complex constraints, algorithm improvement work in multiple academic fields such as CV/NLP, the design and implementation of recommendation architectures for various scenarios, and complex and in-depth analysis of product data. 1. Here, you can get in touch with the cutting-edge recommendation technology in the industry and experience the full-stack development of ultra-large-scale machine learning systems and recommendation systems 2. You can optimize the core modules of Douyin recommendation feed by using cutting-edge technologies, including ranking models, multi-targets, recall, cold start, exploration, etc. 3. The current main research directions include: deep graph neural networks, serialization learning, intelligent deep indexing, deep reinforcement learning, learning to rank, multi-task learning, model compression and acceleration, automl, multimodal recommendation, etc.
Qualifications
1. Excellent data structure and code skills 2. Have a strong interest in recommendation systems or machine learning, and full-stack development of ultra-large-scale systems 3. Excellent problem analysis and problem-solving skills, and passionate about solving challenging problems 4. Familiar with one or more of machine learning, reinforcement learning, natural language processing, and computer vision, and those with experience in recommendation systems, computational advertising, and search engines are preferred.
