Fellow Software Development Engineer, GEMM Optimization

AMD is seeking a Fellow Software Development Engineer to architect and develop features in the tensile-lite assembly code generator for General Matrix Multiplication (GEMM) and GEMM + X (including attention). GEMM performance is one of the most critical levers for AI workload efficiency and this role sits at the center of AMD's effort to deliver best-in-class matrix-multiply performance across current and next-generation hardware. You will own the deep, hardware-aware optimization work that turns AMD's GPU architecture into delivered performance: understanding the hardware specification at the instruction and pipeline level, partnering directly with hardware architects to influence future designs, and innovating algorithms to extract maximum throughput.