Backend Engineer - TikTok Machine Learning Systems

hed to help realize our company vision, building a global platform for creation and communication. We are doing the world-class work in machine learning, computer vision, natural language processing, speech and audio, knowledge and data mining, and transferring our work into TikTok and its affiliates' products which are used by hundreds of millions of users around the world.

As a vital AI infrastructure for the company, our machine learning system integrates our most up-to-date R&D results in AI algorithms and systems. Come and join us, you will get the chance of building large-scale machine learning systems, and working with the best AI system and algorithm researchers and engineers.

Responsibilities

• Research and develop the serving framework of machine learning system, including key computing development, task scheduling, machine learning system management, etc.
• Optimize the deployment and performance of the different model inference, which include but not limited to CV, NLP, Audio task.
• Closely cooperate with the different algorithm teams in TikTok and its affiliates, analysing business bottleneck and optimize for the best software/hardware performance.
• 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 in Computer Science, Engineering or equivalent practical experience
• Master at least one of the following languages in Linux environment: C/C++, Python
• Familiar with at least one state-of-the-art machine learning framework (e.g., Tensorflow, Pytorch);
• Strong analytical abilities and problem solving
• At least 3 years of relevant work experience

Preferred Qualifications

• Practical experience in performance optimization/tuning of deep learning model training/inference.
• Practical experience in CUDA programming and TensorRT
• Familiar with the algorithm details of different deep learning models
• Familiar with model optimization algorithm like quantization and pruning.
• Familiar with TVM, MLIR, XLA or any other model compilation stack

TikTok is committed to creating an inclusive space where employees are valued for their skills, experiences, and unique perspectives. Our platform connects people from across the globe and so does our workplace. At TikTok, our mission is to inspire creativity and bring joy. To achieve that goal, we are committed to celebrating our diverse voices and to creating an environment that reflects the many communities we reach. We are passionate about this and hope you are too.