Senior Deep Learning Hardware Modeling Architect - LPU
Core
Architect and model critical components of NVIDIA's LLM inference solutions to optimize AI inference speed and efficiency through hardware-software co-design.
Role type
Senior IC hardware modeling architect (LLM inference)
Builds
Executable models for LLM inference hardware used by customers across NVIDIA
Domain
AI inference hardware / Deep Learning
Deliverable
production ML models
Required skills
C++ (expert), RTL design, chip architecture concepts, system-level modeling, parallelism, algorithms, data structures
Preferred skills
Systems-level profiling, combined RTL and C++ skillset
Responsibilities
Drive architectural specifications to closure, develop component-level and system-level design specifications, embody specifications in executable models, resolve performance and correctness issues across chip and hardware subsystems
Seniority
Senior, hands-on IC
