AI Systems Performance Architect: Model-Hardware Co-Design

NVIDIA seeks a Senior Nemotron Performance Architect to shape Nemotron models via performance modeling, analysis and forward projections. You will build high-fidelity models to evaluate how architectural choices affect deployment efficiency, ensuring Pareto-optimal trade-offs across accuracy, throughput and interactivity on target platforms.

This role collaborates across research, framework, compiler and hardware teams, requires a Master’s degree, and a strong background in computer