GPU Kernel Development Engineer

Responsibilities

• Optimize deep learning frameworks like TensorFlow and PyTorch for AMD GPUs within open-source repositories.
• Develop and optimize GPU kernels to maximize performance for specific AI operations.
• Design and optimize deep learning models specifically for AMD GPU architectures.
• Collaborate with internal GPU library teams to improve training and inference performance.
• Engage with open-source maintainers to ensure code changes are integrated upstream.
• Optimize performance for both scale-up (multi-GPU) and scale-out (multi-node) distributed computing environments.
• Leverage advanced compiler technologies and graph compilers to enhance the deep learning pipeline.
• Mentor junior team members through code reviews and technical guidance.

Requirements

• Master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
• 5+ years of professional software development experience, specifically in GPU optimization or performance engineering.
• Expertise in C++ and Python development within Linux environments.
• Extensive experience with GPU kernel optimization using HIP, CUDA, or Assembly (ASM).
• Deep understanding of AMD architectures, such as GCN and RDNA.
• Proven experience with deep learning frameworks like TensorFlow and PyTorch.
• Strong knowledge of compiler theory and tools, including LLVM and ROCm.
• Experience in high-performance computing and running large-scale workloads on heterogeneous clusters.

Preferred Qualifications

• Experience using tools like Compute Kernel (CK), CUTLASS, and Triton for multi-platform performance.
• Expertise in debugging, performance tuning, and test design for high-quality software solutions.

About the Company

AMD is a global leader in high-performance computing, graphics, and visualization technologies. Our mission is to build great products that accelerate next-generation computing experiences—from AI and data centers to PCs, gaming, and embedded systems.