NPU Software Engineer Kernel

You will develop optimized compute libraries and neural-network operations for a proprietary ISA. You will expand operation coverage, optimize heterogeneous compute-resource utilization, build architecture-aware kernels for generative AI, and propose features for future compute architectures.

Responsibilities

• Design and develop compute libraries and neural-network operations optimized for the proprietary ISA
• Expand operation coverage across tensor shapes, precision requirements, and numerical stability constraints
• Optimize operation-level performance for heterogeneous compute resources
• Design and implement architecture-aware custom kernels for generative AI workloads
• Propose critical features for next-generation compute architectures

Requirements

• Master’s degree or higher in Electrical Engineering, Computer Science, or a related field
• In-depth understanding of computer architecture and parallel programming
• Strong understanding of neural-network operations and computational dataflows
• Analytical, troubleshooting, and performance-optimization skills
• Proficiency in C++ and Python