SIGN IN
GPU KERNEL OPTIMIZATION ENGINEER jobs in United States
cer-icon
Apply on Employer Site
company-logo

AMD · 18 hours ago

GPU KERNEL OPTIMIZATION ENGINEER

AMD is a company focused on building products that enhance computing experiences across various domains, including AI and gaming. They are seeking a GPU Kernel Optimization Engineer to develop and optimize high-performance GPU kernels for machine learning applications, collaborating with various teams to improve performance and deliver robust solutions.
Embedded SoftwareArtificial Intelligence (AI)SemiconductorCloud ComputingElectronicsHardwareAI InfrastructureComputerEmbedded SystemsGPU
check
Growth Opportunities
badNo H1Bnote

Responsibilities

Analyze the performance of GPU kernels and provide insight on optimization paths
Generate new kernels or optimize existing kernels for matrix multiplication
Communicate and collaborate with key technical experts across AMD and with our partners and customers to improve ROCm applications, libraries, and tools, as well as hardware
Contribute to the design and implementation of AMD’S GPU kernel generator used in a variety of high-performance machine learning libraries and frameworks
Develop optimization and analysis passes on graph representations of GPU kernels
Develop analytical performance models and heuristics for kernel selection
Deliver high-quality code and documentation following best practices for open-source software development
Apply software engineering methodologies to ensure robust, maintainable code
Menor junior engineers and develop technical relationships with peers and partners

Qualification

GPU architectureGPU code optimizationGEMM algorithmsC++ programmingPython programmingLow-level optimizationAgile software developmentWork ethicsMentoring junior engineersCommunication skills

Required

Analyze the performance of GPU kernels and provide insight on optimization paths
Generate new kernels or optimize existing kernels for matrix multiplication
Communicate and collaborate with key technical experts across AMD and with our partners and customers to improve ROCm applications, libraries, and tools, as well as hardware
Contribute to the design and implementation of AMD'S GPU kernel generator used in a variety of high-performance machine learning libraries and frameworks
Develop optimization and analysis passes on graph representations of GPU kernels
Develop analytical performance models and heuristics for kernel selection
Deliver high-quality code and documentation following best practices for open-source software development
Apply software engineering methodologies to ensure robust, maintainable code
Menor junior engineers and develop technical relationships with peers and partners
PhD or Master's degree in Applied Mathematics, Computer Science, Computer Engineering, Electrical Engineering, or equivalent

Preferred

Demonstrate strong knowledge and understanding of GPU architecture
Hands-on professional experience writing and optimizing GPU code
Experience with GEMM algorithms and optimization
Strong background developing applications and libraries in modern C++ and Python
Strong communication skills and work ethics
Experience with best practices in software development, including testing, profiling, debugging, documentation, version control, and issue tracking
Experience with low-level optimization techniques; assembly programming and/or vectorization
Ability to closely interact with technical leads, program managers, and test teams to maintain and release production software
Experience with agile software development practices

Benefits

AMD benefits at a glance.

Company

Advanced Micro Devices is a semiconductor company that designs and develops graphics units, processors, and media solutions.

Funding

Current Stage
Public Company
Total Funding
unknown
Key Investors
OpenAIDaniel Loeb
2025-10-06Post Ipo Equity
2023-03-02Post Ipo Equity
2021-06-29Post Ipo Equity

Leadership Team

leader-logo
Lisa Su
Chair & CEO
linkedin
leader-logo
Mark Papermaster
CTO and EVP
linkedin
Company data provided by crunchbase