NVIDIA
Senior Deep Learning Performance Architect - LPU
$152K–$288K
US, CA, Remote +1 · Senior · Full-time · Posted Aug 11, 2026
- Location
- US, CA, Remote
US, TX, Remote - Experience
- 5+ years of relevant experience.
- Education
- MS or PhD in a relevant field (CS, EE, Math) or equivalent experience.
About the job
Designs GPU and system architectures and performance models to improve AI inference performance and efficiency, informing future hardware architecture decisions.
What you'll do
- Design GPU and system architectures and build power and performance models for AI inference.
- Construct, investigate, and test deep learning algorithms and applications.
- Analyze hardware-software interactions and collaborate across software, research, and product teams to guide future architecture and AI development.
What they ask for
- Strong mathematical foundation in machine learning and deep learning.
- Expert programming skills in C, C++, and/or Python.
- Familiarity with GPU computing (CUDA or similar) and HPC (MPI, OpenMP).
- Strong knowledge and coursework in computer architecture.
Nice to have
- Background in systems-level performance modeling, profiling, and analysis.
- Experience modeling and comparing system-level performance and developing CUDA kernels or compilers for custom ASIC hardware.
Pay
152,000 USD - 241,500 USD base salary (Level 3); 184,000 USD - 287,500 USD base salary (Level 4)
Tools
C, C++, Python, CUDA, MPI, OpenMP
AI focus
Develops performance strategies, models, and architectures for AI inference workloads, including deep learning algorithms and applications.
Model-written summary · the original posting is authoritative