GPU Compute Performance Engineer
Description For GPU Compute Performance Engineer
Apple's Silicon GPU Driver Performance team is seeking an exceptional GPU Compute Performance Engineer to join their elite group responsible for ensuring outstanding GPU performance across Apple's product line. This role sits at the intersection of hardware and software, working directly with GPU architecture and design teams to shape the future of Apple's GPU capabilities.
The position offers a unique opportunity to work on cutting-edge technology, optimizing machine learning workloads and GPU compute applications for Apple Silicon. You'll be involved in all phases of product development, from architectural planning to performance analysis and optimization. The role combines deep technical expertise in GPU architecture with practical application in machine learning and compute workloads.
As a GPU Compute Performance Engineer, you'll work with internal teams on projects like Apple Intelligence and MetalFX, while also collaborating with external partners to optimize their implementations. You'll have the chance to influence hardware roadmaps, ensuring Apple continues to deliver best-in-class GPU performance, particularly in emerging areas like ML training and inference.
This is an ideal position for someone passionate about performance optimization, with a strong background in GPU computing and machine learning. You'll be working with state-of-the-art tools and frameworks, developing solutions that will impact millions of users across Apple's ecosystem. The role offers excellent growth opportunities and the chance to work with some of the industry's best minds in GPU architecture and machine learning.
Responsibilities For GPU Compute Performance Engineer
- Work with internal partners to analyze and improve GPU and system performance of large scale ML deployments
- Optimize GPU based ML algorithm implementations and compute applications for best performance
- Work with hardware teams to define hardware roadmap for GPU performance
- Develop tools and frameworks for performance analysis on Apple Silicon GPUs
Requirements For GPU Compute Performance Engineer
- Experience or interest in emerging GPGPU use cases in ML and compute
- Experience in optimizing compute workloads for GPU performance
- GPU programming with Metal, DirectX, Vulkan, CUDA, Direct Compute, OpenGL, or OpenCL
- Excellent software design and problem solving skills
- Excellent system debugging skills
- Excellent written and oral communication skills
- Experience in ML frameworks such as PyTorch, TensorFlow, JAX (preferred)
- Experience in GPU compute kernel optimization for ML training and inference (preferred)
