Senior AI Inference Performance Engineer — SGLang

Advanced Micro Devices is seeking a performance-focused engineer to push AI inference speed on AMD GPUs using SGLang. You will lead a small, technically deep team, optimizing models from profiling to deployment across customer configurations and ensuring measurable uplifts.

You will own end-to-end responsibility for kernel and system-level optimizations, collaborate with customers, and advance performance methodologies while leveraging AI tools to accelerate workflows across the stack.