Software Engineer in Machine Learning Infra - TikTok Recommendation Architecture

Responsibilities

• Serving and training infra optimization of machine learning models
• Build and maintain high performance online services for TikTok recommendation system
• Build globalized large-scale recommendation system
• Research, design, and develop computer and network software or specialised utility programs
• Analyse user needs and develop software solutions, applying principles and techniques of computer science, engineering, and mathematical analysis
• Update software, enhances existing software capabilities, and develops and direct software testing and validation procedures
• Work with computer hardware engineers to integrate hardware and software systems and develop specifications and performance requirements

Qualifications

• Bachelor's degree or above, majoring in Computer Science, or related fields, with 3+ years of experience building scalable systems.
• Experience at least one or two programming languages in Linux environment such as C/C++/golang;
• Understand GPU hardware architecture, understand GPU software stack (CUDA, cuDNN), and have experience in GPU performance analysis;
• Have experience in deep model inference/training, debugging, tuning, and familiar with model optimization tools such as TVM, MLIR, XLA;
• Familiar with mainstream machine learning frameworks (e.g., Tensorflow, Pytorch, MxNet);