AI System Engineer – New College Grad 2025

The role is for an AI/ML System Performance Engineer at NVIDIA, focusing on optimizing inference strategies and enhancing system performance for AI applications, particularly in datacenter environments.

• Optimize inference deployment to improve accuracy, throughput, and interactivity.
• Develop performance models for algorithmic techniques and hardware optimizations.
• Prioritize features for software and hardware roadmaps based on performance analysis.
• Model performance impact of emerging workflows in Generative AI.
• Collaborate with teams across deep learning research and hardware/software engineering.
• Stay updated on the latest deep learning research.
• Analyze and visualize performance datasets to identify bottlenecks.

• MS or PhD degree in Computer Science, Electrical Engineering, or related fields.
• Strong background in computer architecture and performance analysis.
• Understanding of Machine Learning fundamentals and inference techniques.
• Proficiency in Python (and optionally C++) for data analysis.
• Experience in AI/ML workload evaluation and performance modeling is a plus.
• Ability to work in cross-functional teams and communicate complex analyses.
• Familiarity with GPU computing and deep learning frameworks is advantageous.