AI Systems Development Engineer - AMD

Shape the future of AI with AMD as a Systems Development Engineer. Lead training optimization and inference performance on state-of-the-art GPU architectures.

Join the AMD AI Group as a vital contributor, managing and refining the GPU model execution stack.

Your role will involve developing large-scale training infrastructures, crafting high-performance GPU kernels, and enhancing inference serving. You will collaborate closely with silicon architecture teams and optimize processes that allow AMD GPUs to excel in breakthrough AI model applications.

Key Responsibilities:

• Optimize end-to-end training infrastructure for LLMs on AMD GPUs

• Create resilient data loading and distributed checkpoint systems

• Debug critical issues impacting training performance

• Implement inference serving optimization for cutting-edge workloads

• Collaborate to refine GPU ecosystem and developer tools

Requirements:

• Extensive knowledge in AI/ML training and inference

• Experience with GPU kernel optimization for production

• Familiarity with AMD Instinct MI architecture

• Contributions to open-source AI platforms

• Bachelor's or advanced degree in Computer Science or Engineering

Utilize your expertise in AI systems and GPU technology at AMD, enhancing the capabilities of advanced computing solutions.
#J-18808-Ljbffr