Software Design Engineer - GPU Kernel Optimization
About The Position
As a senior technical member of the team, the Software Design Engineer will design, develop, and optimize high-performance GPU kernels for LLMs and other machine-learning models. The role involves analyzing performance bottlenecks and developing architecture-aware optimizations to maximize compute efficiency, memory-bandwidth utilization, and overall GPU performance. The engineer will collaborate with GPU architecture, compiler, library, framework, model, and infrastructure teams to develop scalable solutions and improve performance across current and next-generation platforms. The position also provides technical leadership, including independently defining goals and scope and driving development efforts and initiatives. This role is not eligible for visa sponsorship. AMD may use artificial intelligence to help screen, assess, or select applicants. The posting is for an existing vacancy.
Requirements
- Strong experience in GPU programming, performance analysis, and system software development.
- Strong C++ and/or Python skills.
- Solid understanding of GPU compute, memory hierarchy, cache behavior, synchronization, and performance bottlenecks.
- Strong experience developing and optimizing GPU kernels using HIP, CUDA, C/C++, or similar technologies.
- Strong analytical and problem-solving skills and pronounced attention to detail.
- Ability to work as a self-starter and independently drive tasks to completion.
- Bachelor’s or master’s degree in computer engineering, computer science, or a related field.
Responsibilities
- Lead optimization of LLMs, quantized models, and emerging AI workloads for AMD GPU architectures.
- Design, implement, profile, and optimize GPU kernels to maximize hardware utilization and application performance.
- Characterize performance across compute, memory bandwidth, cache hierarchy, synchronization, kernel scheduling, and execution efficiency; identify and eliminate bottlenecks.
- Develop compiler-level optimizations and code-generation techniques using LLVM, MLIR, and related technologies to achieve portable and scalable GPU performance.
- Build AI-powered coding agents and automation workflows for kernel generation, optimization, benchmarking, and validation.
- Collaborate with model and infrastructure teams to improve end-to-end AI system performance.
- Define goals and scope, own development efforts, and provide technical leadership while driving projects and initiatives independently.
Benefits
- AMD benefits are referenced as being described in “AMD benefits at a glance”; specific benefits are not listed in the posting.
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
Senior
