Serverless LLM Architect - #1664070

About Huawei Research And Development UK Limited

Founded in 1987, Huawei is a leading global provider of information and communications technology (ICT) infrastructure and smart devices. We have 207,000 employees and operate in over 170 countries and regions, serving more than three billion people around the world.

Our vision and mission is to bring digital to every person, home and organization for a fully connected, intelligent world. To this end, we will drive ubiquitous connectivity and promote equal access to networks; bring cloud and artificial intelligence to all four corners of the earth to provide superior computing power where you need it, when you need it; build digital platforms to help all industries and organizations become more agile, efficient, and dynamic; redefine user experience with AI, making it more personalized for people in all aspects of their life, whether they’re at home, in the office, or on the go.

This spirit of innovation has led Huawei to work in close partnership with leading academic institutions in the UK to develop and refine the latest technologies. With a shared commitment to innovation and progress, both parties have worked together to achieve common goals and establish a strong partnership. The partnership between UK and Huawei help to develop the technologies of the future that will transform the way we all communicate, work and live.

For the past 30 years we have maintained an unwavering focus, rejecting shortcuts and easy opportunities that don't align with our core business. With a practical approach to everything we do, we concentrate our efforts and invest patiently to drive technological breakthroughs.

This strategic focus is a reflection of our core values:

• staying customer-centric,
• inspiring dedication,
• persevering,
• Growing by reflection
  
  

Huawei Research And Development UK Limited Overview

Huawei’s vision is a fully connected, intelligent world. To achieve this, we work to inspire passion for basic research around the world. Our combined passion drives development across the global innovation value chain. Huawei has the largest Research and Development organization in the world with 96,000+ employees in research centers around the globe. In the UK, we already have design centers in Cambridge, London, Edinburgh and Ipswich. We continue to explore and define new research directions and new services. We have expanded our collaborations with academic researchers; researched new network architectures, integration of communications and key enabling technologies; and developed the fundamental theories of these technologies. We invite you to join us on this exciting journey and drive your career forward.

Job Summary

As a pioneer in global technological innovation, Huawei is committed to advancing the development of information technologies and has made remarkable achievements in server and device services, showcasing its strong technological innovation and market reach.

As one of Huawei's pioneers of innovation outside China, Huawei's Edinburgh Research Center focuses on building a next-generation basic software platform and gathers global elites to conduct in-depth research on key technologies such as operating systems, distributed frameworks, databases, programming languages, compilers, knowledge graph, and positioning and navigation. Huawei has made joint technological breakthroughs with Huawei's internal computing product line, HUAWEI CLOUD, and device business domains, and has worked closely with top academic institutions and universities around the world to explore the digital future.

Joining the Huawei Serverless LLM team, you will be in cutting-edge fields such as AI infrastructure, data systems, artificial intelligence, and cloud computing. You will work side by side with global expert teams to meet hundreds of millions of service requirements. Our research results are not only widely used in Huawei's core products, but also will shape the intelligent experience of global users and contribute to the technology enablement world. On an interdisciplinary innovation platform, you will greatly expand your professional horizons, witness and participate in industry transformation, and link your personal achievements to your company's growth.

Key Responsibilities:

• Use serverless methods, including but not limited to cold start optimization, multi-tier storage, and multi-instance distribution optimization, to ensure excellent performance of the LLM service in high-concurrency scenarios, optimize the response speed and resource consumption of the LLM service, and achieve high throughput and low latency in inference. High resource utilization effect of the cluster.
• Explore the next-generation distributed inference engine to ensure high reliability, scalability, and O&M convenience of the system and support large-scale LLM commercial use in the future.
• Track the latest LLM optimization technology to ensure model performance while effectively reducing computing costs, improving loading efficiency, and achieving ultimate system throughput.
• Identify and define future-oriented technical challenges in the serverless LLM field, and enhance technical communication and cooperation with European academia.
• Work closely with cross-functional teams to participate in the innovation of AI infrastructure, data systems, and cloud computing technologies, and promote the commercial application and implementation of Huawei's serverless LLM architecture.
  
  

This job description is only an outline of the tasks, responsibilities and outcomes required of the role. The jobholder will carry out any other duties as may be reasonably required by his/her line manager. The job description and personal specification may be reviewed on an ongoing basis in accordance with the changing needs of Huawei Research and Development UK Limited.

Person Specification:

Required:

• Understand the principles and architecture design of LLMs. Have strong experience in LLM optimization and servitization, including technologies for reducing resource consumption and response delay. Have a good command of LLM service technologies such as cold start optimization, multi-tier storage, and multi-instance distribution optimization. Have a basic command of optimization methods such as model compression, parallel decoding, and KV cache optimization.
• Have a basic command of the distributed system framework and serverless architecture. Have a good command of the core concepts of distributed computing. Have experience in designing and optimizing large-scale distributed cluster systems. Have a basic command of common serverless technologies such as on-demand invoking, automatic expansion, and load prediction and balancing.
• Have experience in large-scale distributed inference and training projects, and focus on performance optimization in cluster scenarios such as training, inference, and hybrid deployment.
• Innovation and technical breakthrough: Be able to independently solve complex technical problems, have the spirit of team leadership and collaboration, be bold in taking responsibilities, and be able to work closely with cross-functional teams to promote the application and commercialization of serverless LLM technology.
  
  

Desired:

• Experience in LLM algorithm optimization is preferred.
• Papers or project achievements related to cutting-edge serverless technologies, and experience in publishing at AI or cloud computing conferences is preferred.
• Familiar with bottom-layer architectures such as distributed systems and OSs is preferred.
  
  

What We Offer

• 33 days annual leave entitlement per year (including UK public holidays)
• Group Personal Pension
• Life insurance
• Private medical insurance
• Medical expense claim scheme
• Employee Assistance Program
• Cycle to work scheme
• Company sports club and social events
• Additional time off for learning and development