Senior Deep Learning Inference Performance Architect
NVIDIA(1 month ago)
About this role
A Senior Deep Learning Inference Performance Architect at NVIDIA focuses on advancing GPU and system-level approaches to improve AI inference performance and efficiency. The role centers on evaluating production large language model performance techniques, informing future GPU architecture decisions, and bridging hardware and software development. It supports the Inference Performance Architecture team in delivering real-time, cost-effective AI inference platforms.
Required Skills
- Deep Learning
- GPU Computing
- CUDA
- C++
- Python
- Performance Modeling
- Profiling
- HPC
- Computer Architecture
- Kernel Development
Qualifications
- MS in CS/EE/Math
- PhD in CS/EE/Math
About NVIDIA
nvidia.comNVIDIA invents the GPU and drives advances in AI, HPC, gaming, creative design, autonomous vehicles, and robotics.
View more jobs at NVIDIA →Apply instantly with AI
Let ApplyBlast auto-apply to jobs like this for you. Save hours on applications and land your dream job faster.
More jobs at NVIDIA
Similar Jobs
2026 Summer Intern - Machine Learning Engineer, AI Kernels (PhD)
General Manufacturing(1 month ago)
SWE, Inference Performance, Onboard
Wayve(11 months ago)
Senior Software Engineer - Model Performance
Inference(1 month ago)
AI Performance Architect
Applied Materials(2 months ago)
Machine Learning Engineer – HPC
Meshy(5 months ago)
Member of Technical Staff, GPU Optimization
Mirage(3 months ago)