A leading data and AI company in San Francisco seeks a Staff Software Engineer to lead kernel-level performance engineering for GenAI workloads. The role involves designing and optimizing high-performance GPU kernels, mentoring engineers, and driving performance roadmaps for low-level compute paths. Ideal candidates should have advanced experience with GPU architectures and performance optimization techniques. This position offers a competitive salary and a chance to work with a talented team focused on pushing the frontier of inference performance.
Qualifications
Experience tuning compute kernels for ML workloads.
Strong knowledge of GPU architecture and memory hierarchy.
Familiarity with ML-specific kernel libraries.
Responsibilities
Lead the design and implementation of compute kernels.
Drive performance improvements and kernel optimizations.
Collaborate with teams to roll out optimizations in production.
Skills
CUDA
GPU acceleration
Deep learning
Performance optimization
Debugging
Education
BS/MS/PhD in Computer Science
Tools
Nsight
NVProf
Job description
A leading data and AI company in San Francisco seeks a Staff Software Engineer to lead kernel-level performance engineering for GenAI workloads. The role involves designing and optimizing high-performance GPU kernels, mentoring engineers, and driving performance roadmaps for low-level compute paths. Ideal candidates should have advanced experience with GPU architectures and performance optimization techniques. This position offers a competitive salary and a chance to work with a talented team focused on pushing the frontier of inference performance.