AI Framework Engineer

AMD
Shanghai
Workplace: OnsiteFull timeCNY 411,670 - 588,100 annuallyFunction: Data Science & Machine LearningExperience: 3+ yearsSkills: ["Problem-solving","Analytical thinking","Proactive approach","Collaboration","Software engineering best practices"]

Develop and optimize deep learning frameworks for AMD GPUs, improving GPU kernels, models, and training/inference performance across multi-GPU and multi-node systems. Build end-to-end distributed inference and RL solutions using mainstream frameworks like vLLM and SGLang, and integrate advanced compiler technologies. Collaborate with internal GPU library teams and open-source maintainers to align changes with requirements and upstream code, while tuning deep learning pipelines for scalability and throughput.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
AMD
AMD
1 day ago

AI Framework Engineer

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 9 hours agoStatus: Live

Job Summary

Develop and optimize deep learning frameworks for AMD GPUs, improving GPU kernels, models, and training/inference performance across multi-GPU and multi-node systems. Build end-to-end distributed inference and RL solutions using mainstream frameworks like vLLM and SGLang, and integrate advanced compiler technologies. Collaborate with internal GPU library teams and open-source maintainers to align changes with requirements and upstream code, while tuning deep learning pipelines for scalability and throughput.
Location: Shanghai
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Mid level

Key Responsibilities

  • •Build and optimize end-to-end distributed inference (including P/D disaggregation and Large-EP) and RL solutions using frameworks like vLLM and SGLang.
  • •Collaborate with internal GPU library teams to analyze and improve training and inference performance on AMD GPUs.
  • •Engage with open-source framework maintainers to align code changes with requirements and integrate upstream.
  • •Optimize deep learning performance across multi-GPU (scale-up) and multi-node (scale-out) systems.
  • •Leverage advanced compiler technologies and improve the deep learning pipeline, including integrating graph compilers.

Pay and Benefits

Salary: CNY 411,670 - 588,100 annually

Key Requirements

  • •3+ years of professional experience in technical software development, focused on GPU optimization, performance engineering, and framework development.
  • •Bachelor’s and/or Master’s in Computer Science, Computer Engineering, Electrical Engineering, or related fields.
  • •Strong C++ development experience within Linux environments.
  • •Ability to define goals, manage development efforts, and deliver high-quality solutions.
  • •Strong problem-solving skills and a keen understanding of software engineering best practices.
Experience:3+ yearsGPU optimizationPerformance engineeringDeep learningLLM frameworksDistributed inference
Education:
Skills:Problem-solvingAnalytical thinkingProactive approachCollaborationSoftware engineering best practices
Tech Stack:C++LinuxDeep learningGPU kernelsMulti-GPUMulti-nodeVLLMSGLangHIPCUDAAssembly (ASM)AMD architecturesGCNRDNACompute Kernel (CK)CUTLASSTritonGraph 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