Responsibilities
Team introduction: ByteDance's recommendation architecture team is responsible for the design and development of the recommendation system architecture of the relevant products under ByteDance, ensuring the stability and high availability of the system responsible for online services and offline data flow performance optimization, solving system bottlenecks, and reducing cost and overhead abstract general components and services of the system, building recommendation middle platforms and data middle platforms, supporting the rapid incubation of new products and empowering ToB. 1. Participate in the research and development and optimization of large-scale machine learning online estimate framework to support efficient model reasoning of ByteDance related products such as Toutiao and Douyin 2. Participate in the research and breakthroughs of large-scale features and samples processing and circulation, model training and scheduling and other related issues 3. Work closely with students in the recommendation algorithm to analyze and solve the above problems and tasks, and feed back to actual business.
Qualifications
1. Proficient in C/C++ programming in Linux environment 2. Familiar with operating system knowledge and computer architecture 3. Understand the underlying framework implementation of some mainstream machine learning framework TENSORFLOW/PYTORCH, etc. [Plusty points] 1. Have practical experience in the prediction and training of deep learning models 2. Implement custom operators or optimize existing operator implementations 3. Be familiar with model pruning, quantization and compression methods 4. Participate in the work of combining software and hardware optimization.
