Principal Architect - AI Workload & Architecture Intelligence

Huawei Canada has an immediate permanent opening for a Principal Architect.

About the team: 

The Computing Data Application Acceleration Lab aims to create a leading global data analytics platform organized into three specialized teams using innovative programming technologies. This team focuses on full-stack innovations, including software-hardware co-design and optimizing data efficiency at both the storage and runtime layers. This team also develops next-generation GPU architecture for gaming, cloud rendering, VR/AR, and Metaverse applications.

One of the goals of this lab are to enhance algorithm performance and training efficiency across industries, fostering long-term competitiveness.

• Cutting-edge AI technology Analysis: Research on emerging AI architectures such as World Models, Agents, and Multimodal Foundation Models.
• Analyze the computational characteristics of autonomous intelligent systems such as AutoGPT and AI Agents. 
• Study the workload characteristics of next-gen transformer architectures (such as MoE, SSM, etc.).
• Track new applications such as AI+ scientific computing.
• Hardware-oriented workload analysis: Establish a framework for mapping AI applications to hardware requirements. 
• Extract key computing patterns and convert them into hardware design requirements. 
• Provide architecture recommendations for customized AI accelerators. 
• Assess the impact of new storage and interconnect architectures on AI performance.
• System-level optimization suggestions: Provide system architecture improvement suggestions based on workload analysis. 
• Design customized acceleration solutions for specific AI applications. Assist in developing technology roadmaps for chips and systems.

About the ideal candidate：

• Technical requirements: Proficient in the latest AI model architecture (World Models, MoE, Agents, etc.) Familiar with AI chip architecture (such as GPU, NPU, and TPU) Understand the memory hierarchy and interconnect technologies. Experience in system architecture design.
• Tool capabilities: Master the underlying implementation of AI frameworks (such as PyTorch and JAX). Familiar with hardware performance analysis tools. Capable to develop simulators or analysis tools.
• Background of the study: PhD preferred in AI architecture, computer architecture related fields Solid publication records in the field of AI systems or chip design. Experience in deploying large-scale AI systems is a great asset.

#LI-SZ2