Responsibilities
Team Introduction: We are the Doubao Video Generation Model-PixelDance team. We focus on developing video generation models and solving key problems in video generation, including but not limited to high-dynamic video generation and content consistency assurance. Build industry-leading video basic models and lead the future trend of technology. The work of the video generation engineering team involves the full cycle process of model production. Here, you have the opportunity to participate in every link of model data production, training acceleration, inference acceleration, and service deployment. At the same time, you will be exposed to the most advanced video generation technology, massive data, and large-scale clusters. We hope that you can scale up with our models. 1. Responsible for the performance optimization of LLM and Diffusion Model 2. Through performance optimization methods such as TensorRT, quantization, pruning, operator fusion, CUDA operator writing, etc., combined with business needs, GPU performance is maximized 3. Responsible for the research and introduction of ByteDance Research's inference optimization technology 4. Deeply cooperate with the algorithm department to jointly optimize the algorithm and system.
Qualifications
1. Bachelor degree or above, major in computer/electronics/automation/software, etc., those with experience in AI engineering optimization are preferred 2. Proficient in C/C++, algorithms and data structures, and familiar with Python 3. Proficient in GPU high-performance computing optimization technology, in-depth understanding of computer architecture, familiar with parallel computing optimization, memory access optimization, low-bit computing, etc. 4. Have rich experience in CUDA-based GPU performance optimization 5. Understand the basic principles of deep learning algorithms, be familiar with the basic architecture of neural networks and the calculation methods of each operator, and understand at least one deep learning training framework and the analysis of its model files, such as Pytorch and Tensorflow 6. Familiar with TensorRT-LLM, ORCA, VLLM, etc. understand the mainstream LLM and Diffusion Model, and those with LLM and Diffusion Model acceleration optimization experience are preferred.
