AI/ML Silicon Accelerator Memory Architect

The Principal/Distinguished Architect role defines the end-to-end memory and data transport architecture for AI/ML accelerators, spanning memory technology selection, controller design, on-die networks, and DMA engines. This position involves owning the complete data path across multiple silicon generations, conducting performance-versus-power analysis, and collaborating with internal teams and external vendors. The role requires deep expertise in memory subsystems, data movement architectures, and system-level simulation to drive architectural decisions.