Deep Learning Performance Architect

Responsibilities

• Benchmark and analyze performance of various machine learning and deep learning workloads across GPU- and NPU-based architectures
• Build and validate performance models to deliver projections and insights for LLM and Generative AI workloads on emerging architectures
• Identify architecture, software, and system performance bottlenecks and propose actionable optimizations
• Explore and evaluate new software and hardware capabilities to translate them into measurable application gains
• Leverage AI agents to accelerate performance investigation and engineering workflows

Requirements

• BSc, MS, or PhD in Computer Science, Electrical Engineering, Mathematics, or a relevant discipline
• Strong background in computer architecture
• Familiarity with GPU or accelerator-based deep learning platforms and software stacks
• Knowledge of LLM or generative AI algorithms and kernel optimizations
• Experience in system architecture design and performance optimization
• Familiarity with machine learning and deep learning frameworks
• Hands-on experience using AI agents to assist daily engineering work

About the Company

NVIDIA is developing processor and system architectures that accelerate deep learning on edge devices, workstations, and data center GPUs for a variety of applications including automotive, robotics, large language models, and AI generative models.