Senior Performance Engineer

NVIDIA, a company that has been driving innovation in computer graphics, PC gaming, and accelerated computing for over 25 years, is seeking a Senior Performance Engineer to join its DGX Cloud AI Efficiency Team. This team is responsible for advancing the performance, efficiency, and resiliency of large-scale AI workloads, and the successful candidate will play a key role in this effort. The main day-to-day responsibilities of this role include analyzing the end-to-end performance of large-scale AI workloads, designing and executing performance studies, and defining evaluation methodologies and success metrics. The successful candidate will also use profiling, observability, and data analysis to inform optimization plans, and partner with various teams to validate and deliver performance improvements. To be considered for this role, candidates must have a BS or higher degree in computer science, computer engineering, or a related field, with at least 12 years of experience. They must also have strong programming skills in C++ and Python, a solid foundation in operating systems, computer architecture, and distributed systems, and experience with performance engineering and optimization of complex software or systems. The ideal candidate will have experience analyzing large-scale AI clusters or distributed training and inference workloads, as well as experience with CUDA, GPU computing systems, and GPU performance analysis. Hands-on experience with deep learning frameworks such as PyTorch or JAX/XLA, and a deep understanding of system-level performance analysis, workload characterization, and optimization, are also desirable. NVIDIA offers a unique opportunity to work with a technically diverse team of infrastructure experts to unlock more efficient AI at scale, and to contribute to groundbreaking developments in Artificial Intelligence, High-Performance Computing, and Visualization.