Principal Scientist - Software/Hardware Co-design

Our team has an immediate permanent opening for a Principal Scientist.Responsibilities:Cooperate with the AI expert team to guide the design of the next-generation chip including computing power ratio, memory, cache and networking based on the characteristics of future AI workloads for the objectives of throughput, scalability, and stability.Build an accurate and universal AI performance model based on mainstream AI acceleration technologies to support theoretical analysis.Track the emerging hardware designs in the industry, conduct in-depth insight and survey analysis, and identify the direction of key cutting-edge technologies.What you’ll bring to the team:Master's or Doctoral degree in Computer Science or Electronic Engineering.At least 5+ years of chip design experience, and experience in AI accelerator/massively parallel computing system design is an asset.Deep understanding of the basic principles of deep learning, familiar with chip microarchitecture, the latest AI software stack (kernels, compilers, acceleration libraries) and mainstream large model training and inference algorithms, such as 3D parallelism, low precision data formats, etc. #J-18808-Ljbffr