Principal Architect - AI Workload & Architecture Intelligence

Huawei; Markham; On-site; CAD 125,000 - 150,000; Full time

Job summary

An established industry player is seeking a Principal Architect to drive innovation in AI technology. This role involves cutting-edge research on AI architectures and their integration into hardware solutions, focusing on enhancing performance and efficiency. The ideal candidate will possess a deep understanding of AI models, system architecture, and hardware design, contributing to the development of next-generation AI systems. Join a dynamic team dedicated to pushing the boundaries of technology in the fields of gaming, cloud rendering, and the Metaverse. If you're passionate about AI and architecture, this is an exciting opportunity to make a significant impact.

Qualifications

• Proficient in latest AI model architectures and AI chip architecture.
• Experience in system architecture design and workload analysis.

Responsibilities

• Research on emerging AI architectures and analyze computational characteristics.
• Provide architecture recommendations for customized AI accelerators.

Skills

AI model architecture

System architecture design

Research skills

Hardware performance analysis

Workload analysis

Education

PhD in AI architecture or computer architecture

Tools

PyTorch

JAX

Hardware performance analysis tools

Job description

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 is to enhance algorithm performance and training efficiency across industries, fostering long-term competitiveness.

About the job:

• 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 of developing 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.