Staff Software Engineer - GenAI Performance and Kernel

What this role involves

This role focuses on designing, implementing, and optimizing high-performance GPU kernels for GenAI inference. The engineer will lead kernel development, drive performance improvements, and mentor others. They will work closely with ML researchers and systems engineers to push inference performance at scale.

Skills this posting asks for

• cuda
• triton
• opencl
• llvm ir
• assembly
• gpu architecture
• tiling
• blocking
• software pipelining
• vectorization
• fusion
• loop transformations
• auto-tuning
• cublas
• cudnn
• cutlass
• onednn
• nsight
• nvprof
• perf
• vtune
• mixed precision
• quantization
• sparsity

Requirements

• Level: staff

From the employer’s posting

P-1285 About This Role As a staff software engineer for GenAI Performance and Kernel, you will own the design, implementation, optimization, and correctness of the high-performance GPU kernels powering our GenAI inference stack. You will lead development of highl…