General Information

Req #
WD00071318
Career area:
Software Engineering
Country/Region:
China
State:
Guangdong
City:
深圳(Shenzhen)
Date:
Tuesday, September 10, 2024
Working time:
Full-time
Additional Locations
* China - Guangdong - 深圳(Shenzhen)

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$57 billion revenue global technology powerhouse, ranked #248 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). 

This transformation together with Lenovo’s world-changing innovation is building a more inclusive, trustworthy, and smarter future for everyone, everywhere. To find out more visit www.lenovo.com, and read about the latest news via our StoryHub.

Description and Requirements

职位描述:

1.    异构计算部署,将不同的AI模型(如LlamaQwenBCAI APP等)适配到异构计算平台(CPU/GPU/NPU等),以找到性能最佳的部署方案。

2.    通过模型/算法/系统优化(量化、压缩等)和架构优化,优化异构计算平台的性能。

3.    分析异构平台性能瓶颈问题,并找出有效的解决方案。

4.    支持/协作相关团队评估异构计算平台解决方案的有效性和影响,确定测试方法和标准。

任职要求:

1.    计算机科学、电子学或相关领域学士及以上学位,精通PythonC++等编程语言。

2.    熟悉异构计算平台,深入了解CPU/DGPU/NPU架构,掌握性能优化方法,具有异构计算平台性能分析经验。

3.    熟悉深度学习框架,如TensorFlowPyTorchOpenVINOTensorrt等,用于AI性能加速。

4.    熟悉深度学习模型优化技术,如量化、压缩等。

5.    良好的英语口语和沟通能力,以便有效地与跨部门团队合作。

Job description:
1.  Heterogenous computing deployment, adapt different AI models(Llama/Qwen/BC/AI APP…) to heterogenous computing platform(CPU/GPU/NPU…) to find the deployment solution with best performance
2.  Optimize the heterogenous computing platform performance through model/algorithms/system optimization(quantization, compression…) and architecture optimization 
3.  Analyze heterogenous platform performance bottleneck issue and figure out effective solution
4.  Support/collaborate with related teams to evaluate the effectiveness and impact of heterogenous computing platform solution to define test method and criteria

Skill required:
1.  Bachelor’s degree or above in Computer Science, Electronics, or related fields, strong programming skills in languages such as Python, C++, or similar
2.  Familiar with heterogenous computing platform
well know CPU/dGPU/NPU architecture and master performance optimization method, experience with heterogenous computing platform performance analysis
3.  Familiar with deep learning frameworks such as TensorFlow/PyTorch/OpenVINO or TensorRT and so on for AI performance acceleration 
4.  Familiar with deep learning model optimization techniques such as quantization, compression and so on
5.  Good spoken English and communication skills to collaborate effectively with across teams

Additional Locations
* China - Guangdong - 深圳(Shenzhen)
* China
* China - Guangdong
* China - Guangdong - 深圳(Shenzhen)