SMTS Software System Design Eng. AI软件系统工程师 Job Listing at AMD in Shanghai (Job ID 57772-en-us)

Description

WHAT YOU DO AT AMD CHANGES EVERYTHING

We care deeply about transforming lives with AMD technology to enrich our industry, our communities, and the world. Our mission is to build great products that accelerate next-generation computing experiences – the building blocks for the data center, artificial intelligence, PCs, gaming and embedded. Underpinning our mission is the AMD culture. We push the limits of innovation to solve the world's most important challenges. We strive for execution excellence while being direct, humble, collaborative, and inclusive of diverse perspectives. 

AMD together we advance_

THE ROLE: 

As an AI software system design engineer, you are responsible for machine learning software development program technical support for AMD server GPU.

THE PERSON: 

Success in this role requires knowledge of a domain expert in at least two or more areas including AI inference/training workloads; AI frameworks; GPU computing, architecture, toolchain, driver and communication; and C++/python development/debugging, etc.

The candidate needs to have hands-on experiences with AI models, end-to-end pipeline, industry framework / SDKs and solutions.

KEY RESPONSIBILITIES: 

• Position technical proposals and support to top customers.
• Provide significant contribution to customer PoC success.

• Drive custom requirements for AI SW, including from POC requirement communication to POR release, from GPU kernel to KMD/UMD(ROCm) to frameworks (like TensorFlow, PyTorch, vLLM, sglang, etc.)

• Collaborate and interact with different teams to analyze and optimize training and inference workloads 
• Analyze competitive solutions to identify strength and weakness for articulate value propositions.
• Apply your knowledge of software engineering best practices 

PREFERRED EXPERIENCE: 

• Ability to work independently, define project goals and scope, and lead your own development effort. 
• Solid communication skills, in both English and mandarin. 
• Excellent programming skills in Python, C, or C++ and software skills, including debugging and performance analysis. 
• Experience with parallel programming, ideally CUDA C/C++, HIP or computer shader.
• Experience with AI inference/training workloads (i.e. search, advertising, referral business infrastructure, or large model business infrastructure).
• Experiences with AI frameworks/tools(e.g. Pytorch, Tensorflow, vLLM,TensorRT-LLM, Megatron-LM, Deepspeed, TensorRT).
• Experience with model inference optimization process like gemm/convolution tuning, graph optimization and operator fusion.
• Experience with GPU profiling and AI framework like PyTorch and TensorFlow.
• Experiences with GPU kernel primitive like convolution, FA, PA, fused MOE, development with triton, cutlass.
• Experiences with Linux OS/driver, CI and toolchain (profiler/DCGM) development and debugging.
• Knowledge of Linux DRM, HSA, ROCm KMD/UMD driver is a plus.
• Knowledge of multi-GPU and multi-node collective communication primitives.
• Knowledge of compiler (triton/TVM) is a plus.

ACADEMIC CREDENTIALS: 

• Bachelor's or Master's in Electrical Engineer, Computer Engineering, Computer Science, or a closely related field 

#LI-FL1

Benefits offered are described:  AMD benefits at a glance.

AMD does not accept unsolicited resumes from headhunters, recruitment agencies, or fee-based recruitment services. AMD and its subsidiaries are equal opportunity, inclusive employers and will consider all applicants without regard to age, ancestry, color, marital status, medical condition, mental or physical disability, national origin, race, religion, political and/or third-party affiliation, sex, pregnancy, sexual orientation, gender identity, military or veteran status, or any other characteristic protected by law.   We encourage applications from all qualified candidates and will accommodate applicants' needs under the respective laws throughout all stages of the recruitment and selection process.