Used Tools & Technologies
Not specified
Required Skills & Competences ?
Python @ 4 Debugging @ 7 Reporting @ 4 CUDA @ 4 GPU @ 4Details
We are seeking a Senior GPU Kernel Performance Lead to oversee performance analysis and reporting of GPU kernel performance. This role supports NVIDIA's high-performance GPU math kernels used in deep learning models, including cuDNN, cuBLAS, and TensorRT, and focuses on maximizing performance and energy efficiency of current and future-generation GPUs.
Responsibilities
- Specify test cases derived from Deep Learning workloads to ensure coverage across all kernels on simulation and silicon targets
- Develop and use analytical models to determine performance theory
- Track and report kernel performance throughout development lifecycle, expanding current infrastructure
- Provide feedback to kernel developers on performance regressions and optimization opportunities
Requirements
- PhD in Computer Science, Computer Engineering, Applied Math, or related field (or equivalent experience) with 8+ years relevant industry experience
- Strong C++ programming and software design skills including debugging, performance analysis, and test design
- Experience leading or managing a team focused on performance of CPUs, GPUs, or DL accelerators
Ways to Stand Out
- Experience with analytical models and cycle-accurate hardware simulators
- Knowledge of performance tools like Nsight or VTune
- Programming experience in assembly, MLIR/LLVM, Python, CUDA/OpenCL beyond C++
Benefits
- Competitive base salary range $224,000 - $425,500 USD, determined by location, experience, and internal benchmarks
- Eligibility for equity and other NVIDIA benefits
Join NVIDIA’s Deep Learning Architecture team and help build real-time, cost-effective AI computing platforms driving advancements in AI fields.