Lenovo

■Roles and responsibilities

Lenovo Research (LR) is the R&D division of Lenovo and has always been committed to pushing forward the development of information technology, smart devices, and services, keeping delivering cutting-edge technologies that have been built into Lenovo’s high-tech products and services.

This position is to work as an NPU inference engineer in a team of PC Innovation and Ecosystem (PCIE) Lab, research industry architecture and develop Lenovo universal inference platform to support all Lenovo models and dNPU hardware.

We are looking for a passionate candidate who is experience in dNPU tools chain and model structure.

Role and Responsibility

• Responsible for the research and development of AI algorithms, including but not limited to deep learning, machine learning, natural language processing and other related algorithms.
• Participate in the requirement analysis and decomposition of the reasoning system and cooperate with the architecture team to gradually improve the hardware and software architecture.
• According to project requirements, familiar with the corresponding algorithm model, and optimize and improve it.
• Responsible for writing and maintaining relevant technical documents

■Key Interaction with:

• Lenovo Research in Beijing – software, system research
• Lenovo Research in Tianjin – software, system research
• Lenovo Research in Shenzhen – hardware development, electronical engineering

Requirements

Must Have – essential

Experience

• MSc or PhD in computer/information science, electronics engineering, or a related field
• 8+ years’ R&D experience in model inference
• Excellent problem analysis and solution ability

Skill, Competency

• Basic and advanced computer vision algorithm design
• Written communication skills in business English for efficient communication with team
• Basic English communication skills
• C/C++, Python and other programming languages, with good programming habits and code norms.
• Linux/Windows platform development experience

Good to have - desirable

Experience

• Experience of collaborating with other researchers or engineers in a global work environment
• Experience of solving problems in the inference of various models

Skill, Competency

• Experience with machine learning, deep learning frameworks like ONNX, GGML, OpenVINO, Tensorflow, PyTorch
• Experience with model optimization like model fixed-point quantization, sparse computing
• Experience with OpenCL, DirectML, CUDA code on GPU, NPU or FPGA
• Experience with AI algorithms and models, such as Transformer, CNN, SD, LAM