General Information

Req #
100016507
Career area:
Engineering
Country/Region:
China
State:
Beijing
City:
北京（Beijing）
Date:
Wednesday, December 17, 2025
Additional Locations: 
* China

Why Work at Lenovo

We are Lenovo. We do what we say. We own what we do. We WOW our customers.

Lenovo is a US$69 billion revenue global technology powerhouse, ranked #196 in the Fortune Global 500, and serving millions of customers every day in 180 markets. Focused on a bold vision to deliver Smarter Technology for All, Lenovo has built on its success as the world’s largest PC company with a full-stack portfolio of AI-enabled, AI-ready, and AI-optimized devices (PCs, workstations, smartphones, tablets), infrastructure (server, storage, edge, high performance computing and software defined infrastructure), software, solutions, and services. Lenovo’s continued investment in world-changing innovation is building a more equitable, trustworthy, and smarter future for everyone, everywhere. Lenovo is listed on the Hong Kong stock exchange under Lenovo Group Limited (HKSE: 992) (ADR: LNVGY). 

To find out more visit www.lenovo.com and read about the latest news via our StoryHub.

Description and Requirements

Job Responsibilities：
1. Design and develop AI local inference code to support large-scale deployment scenarios.
2. Conduct architecture design and implement acceleration solutions for heterogeneous hardware platforms (including iGPU and d-GPU).
3. Optimize inference performance by applying advanced technical methods such as operator fusion, memory bandwidth reduction, quantization, and mixed precision.
4. Engage in device perception algorithm development and LLM performance fine-tuning.
5. Drive technological innovation in inference acceleration algorithms and maintain technical leadership in the field.

Job Requirements：
1. Profound professional knowledge and practical experience in AI local inference code development and large-scale deployment.
2. Solid expertise in architecture design of heterogeneous hardware platforms (iGPU/d-GPU) and hands-on experience in implementing corresponding acceleration solutions.
3. Proficient in applying advanced optimization techniques (operator fusion, memory bandwidth reduction, quantization, mixed precision, etc.) to improve inference performance.
4. Rich experience in device perception algorithm development and LLM performance fine-tuning.
5. Demonstrated ability in technological innovation of inference acceleration algorithms and a track record of maintaining technical leadership.
6. Strong problem-solving skills and the ability to independently tackle technical challenges in related fields.

Additional Locations: 
* China
* China
Go back