AI Software Engineer — High-Performance

AMD
Shanghai
Workplace: OnsiteFull timeCNY 309,400 - 442,000 annuallyFunction: Software EngineeringExperience: 3+ yearsEducation: mastersSkills: ["Problem-solving","Collaboration","Independent work","Proactive approach","Software engineering best practices"]

Optimize and develop deep learning frameworks for AMD GPUs, improving GPU kernels, model performance, and training/inference efficiency across multi-GPU and multi-node systems. Collaborate with internal GPU library teams and open-source maintainers to integrate end-to-end optimizations into mainstream LLM and RL frameworks (e.g., vLLM, SGLang). Apply cutting-edge compiler technologies and software engineering best practices to deliver maintainable, high-performance solutions.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
AMD
AMD
7 hours ago

AI Software Engineer — High-Performance

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 4 hours agoStatus: Live

Job Summary

Optimize and develop deep learning frameworks for AMD GPUs, improving GPU kernels, model performance, and training/inference efficiency across multi-GPU and multi-node systems. Collaborate with internal GPU library teams and open-source maintainers to integrate end-to-end optimizations into mainstream LLM and RL frameworks (e.g., vLLM, SGLang). Apply cutting-edge compiler technologies and software engineering best practices to deliver maintainable, high-performance solutions.
Location: Shanghai
Workplace: Onsite
Employment Type: Full time
Job Function: Software Engineering
Seniority: Mid level

Key Responsibilities

  • •Build and optimize end-to-end distributed inference and RL solutions on mainstream frameworks like vLLM and SGLang.
  • •Work with internal GPU library teams to analyze and improve training and inference performance on AMD GPUs.
  • •Engage with open-source maintainers to ensure code changes align with requirements and integrate upstream.
  • •Optimize deep learning performance for both multi-GPU scale-up and multi-node scale-out distributed computing environments.
  • •Leverage cutting-edge compiler technologies to improve deep learning performance and enhance the full pipeline, including integrating graph compilers.

Pay and Benefits

Salary: CNY 309,400 - 442,000 annually

Key Requirements

  • •3+ years of professional experience in technical software development focused on GPU optimization, performance engineering, and framework development.
  • •Strong C++ development experience in Linux environments, with debugging, performance tuning, and test design to deliver maintainable software.
  • •Hands-on GPU kernel design and optimization for deep learning on AMD GPUs using HIP, CUDA, and assembly (ASM), with knowledge of AMD architectures (GCN, RDNA).
  • •Experience integrating optimized GPU performance into ML/LLM frameworks such as vLLM, SGLang, TensorFlow, and PyTorch to accelerate training and inference.
  • •Foundational compiler understanding (e.g., LLVM, ROCm) and experience optimizing deep learning pipelines, including graph compiler integration.
Experience:3+ yearsDeep learningLLMGPU optimizationHigh-performance computingDistributed computing
Education:Master's in Computer Science, Computer Engineering, Electrical Engineering, or related fields
Skills:Problem-solvingCollaborationIndependent workProactive approachSoftware engineering best practices
Tech Stack:C++LinuxPythonHIPCUDAASMGPU kernelsGCNRDNACompute Kernel (CK)CUTLASSTritonVLLMSGLangTensorFlowPyTorchGraph compilersLLVMROCm

Company Brief

AMD
Designs and produces semiconductor products including CPUs, GPUs, and adaptive SoCs for consumer, enterprise, and embedded markets, competing across PCs, data centers, and gaming industries.
Industry: Electronics Manufacturing
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Public Company
Valuation: Public Company (Market Cap in USD)
Funding: IPO / Publicly Listed
Headquarters: Santa Clara, United States
Founded: 1969
Glassdoor
Glassdoor: 3.9
WebsiteLinkedIn