NVIDIA
Senior Software Engineer, CUTLASS Performance
$152K–$288K
US, CA, Santa Clara +4 · Senior · Full-time · Posted Jun 1, 2026
- Location
- US, CA, Santa Clara
US, TX, Austin
US, OR, Hillsboro
US, NC, Durham
US, WA, Redmond - Experience
- 3+ years of relevant industry experience.
- Education
- Master's or PhD degree in Computer Science, Computer Engineering, or related field (or equivalent experience).
About the job
Benchmark and optimize CUTLASS GPU kernels for deep learning workloads, building tools to analyze performance and coordinating improvements across NVIDIA teams.
What you'll do
- Benchmark deep learning inference and training to identify GPU kernel and fusion opportunities.
- Analyze theoretical versus realized performance and recommend software or model changes.
- Develop tools to automate benchmarking and optimization; represent CUTLASS performance with partner teams.
What they ask for
- Strong programming skills in Python and C++.
- Experience in software performance analysis and optimization.
- Deep understanding of computer architecture and familiarity with GPUs or similar parallel processing architectures.
Nice to have
- Deep understanding of state-of-the-art DL model architectures.
- Hands-on performance benchmarking of DL frameworks, or experience developing performance models and regression systems.
Pay
152,000 USD - 241,500 USD base salary (Level 3); 184,000 USD - 287,500 USD base salary (Level 4)
Tools
CUTLASS, C++, Python, PyTorch, JAX, SGLang, vLLM, TRT-LLM
AI focus
Benchmarks and optimizes GPU kernels for deep learning model inference and training. NVIDIA also states it uses AI tools in recruiting.
Model-written summary · the original posting is authoritative