Computing Network & System Architecture Group Leader

Описание

This role is for a Group Leader in the System & Network Architecture Team within Huawei's Computing Network Innovation Lab, focusing on next-generation computing network architecture research for AI and HPC data centers. The mission is to achieve differentiated competitiveness in high-performance computing cluster network infrastructure.

Responsibilities

• Deeply analyzing the advantages and disadvantages of mainstream network systems to find opportunities for network architecture innovation
• Insight into the technology developing trend of the high-performance computing network field and leading the corresponding technology planning
• Exploring new architectures of high-performance computing network systems and efficiently integrating communication library, topology, and network protocol to solve performance bottlenecks
• Analyzes computing cluster network performance and leads the development of computing cluster network technologies
• Research and optimize the heterogeneous interconnection topology of key computing chips to continuously improve the key competitiveness of Huawei computing heterogeneous chipsets
• Responsible for the research of data center network technologies and guide network topology design and routing algorithm development
• Lead the development of a comprehensive system architecture for AI Fabric and HPC Fabric solutions
• Manage and mentor highly skilled team leaders to ensure that the group operates together in pursuit of common goal
• Foster a collaborative and innovative work environment
• Provide technical guidance and support to team members
• Collaborate closely with cross-functional teams internationally, including hardware, software, and ucode design teams, to ensure alignment of architectural decisions with product and platform common objectives
• Initiate and supervise collaborations with top academic researchers in Israel and abroad
• Stay up to date with emerging technologies and industry trends in AI, HPC and big data industries
• Evaluate and recommend technologies and next generation projects
• Occasional travel related to ongoing projects, seminars, conferences etc.

Requirements

• At least 10 years of hands-on experience in system architecture design, or equivalent research experience
• Demonstrated experience in leading R&D team
• Familiarity with high-performance computing cluster services and system architectures, such as AI, HPC and big data
• In-depth understanding of computer networks, communication libraries, and design of AI or HPC cluster networks
• Ability to work in a team environment; actively seek out resolution to issues with the team and work co-operatively to build a coherent system
• Team-working and excellent inter-personal communication skills
• High level of self-reliance and an autonomous target-oriented work style, “can do” attitude, eager to learn new things and ready to think outside the box
• Ability to work on a schedule, even for un-schedule-able issues such as inventiveness
• Experience with network system of AI, HPC or big data cluster
• Demonstrated capability in several items from the list below:
• Deep understanding of computer network protocol and network topology of computing cluster
• Familiarity with communication library, such as OpenMPI/NCCL
• Extensive experience in leading the network architecture design of computing cluster
• Experience with implementing routing algorithm
• Familiarity with network specifications of CPU/Network Processing Unit/ Neural Processing Unit/Switch chip
• Fluent in written and spoken English

Nice to have

• You hold a Doctor’s degree or above in the field of computer science, electrical and electronic engineering or in a similar background in Research & Development
• Publications in reputed journals and conferences