Deep Learning Kernel Software Performance Architect
Core
Architect and optimize GPU kernel performance for state-of-the-art data-center deep learning platforms, building automated workflows to detect and prevent performance regressions.
Role type
Senior IC software performance architect (GPU kernels)
Builds
Automated performance testing workflows, regression infrastructure, and optimized GPU-accelerated kernels for deep learning workloads.
Domain
Data center infrastructure + GPU computing + Deep Learning
Deliverable
production ML models
Required skills
Python, C/C++, computer architecture, parallel programming, performance analysis, profiling, regression triage, automation scripting
Preferred skills
High-performance kernel development (GEMM/Attention/CUTLASS), CUDA programming, ML/DL workload expertise, analytical modeling
Technologies
Python, C/C++, CUDA, CI/CD pipelines, GPU-accelerated kernels
Responsibilities
Analyze and optimize GPU-accelerated kernel performance against baselines; debug performance issues end-to-end; develop Python-based automation for performance testing and analysis; design and operate large-scale performance test workflows; collaborate with kernel developers, compiler teams, and architecture groups to align performance checks with release needs.
Seniority
Senior, hands-on IC
