AI Software Engineer, LLM Inference Performance Analysis - New College Grad 2026

A Software Engineer, Performance Analysis and Optimization for LLM Inference at NVIDIA focuses on improving the efficiency and scalability of large language model inference on NVIDIA computing platforms. The role centers on advancing compiler and kernel infrastructure to shape runtime behavior and hardware utilization for next-generation LLM deployments across data center and embedded platforms. The position requires close collaboration with compiler, hardware, kernel, and framework teams and influences performance of deployed models.