GPU KERNEL OPTIMIZATION ENGINEER
About The Position
At AMD, our mission is to build great products that accelerate next-generation computing experiences—from AI and data centers, to PCs, gaming and embedded systems. Grounded in a culture of innovation and collaboration, we believe real progress comes from bold ideas, human ingenuity and a shared passion to create something extraordinary. When you join AMD, you’ll discover the real differentiator is our culture. We push the limits of innovation to solve the world’s most important challenges—striving for execution excellence, while being direct, humble, collaborative, and inclusive of diverse perspectives. Join us as we shape the future of AI and beyond. Together, we advance your career. THE ROLE: AMD is seeking a talented and motivated computer scientist, software developer, and optimization engineer to work on GPU kernels used in various LLMs and machine learning applications as part of the AMD Radeon Open Ecosystem (ROCm). As a key contributor you will develop, profile, or optimize high-performance GPU kernels for General Matrix Multiplication (GEMM). In this role you will be collaborating with teams involved with all aspects of machine learning and math libraries. THE PERSON: We are looking for a talented library developer who is looking to make an impact on deep learning performance. A great candidate will be a strong collaborator who is open to continuous learning, working independently, and is excited about developing innovative solutions.
Requirements
- 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
- PhD or Master’s degree in Applied Mathematics, Computer Science, Computer Engineering, Electrical Engineering, or equivalent
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
Benefits
- AMD benefits at a glance.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Education Level
Ph.D. or professional degree
