2 days ago
Responsibilities
- Analyze end-to-end performance across compute, networking, storage, and software stacks for large-scale AI workloads.
- Design and execute performance studies, benchmarks, baselines, and efficiency evaluations.
- Diagnose regressions and bottlenecks using profiling, observability, and data analysis.
- Develop prioritized optimization plans and drive performance improvements through deployment.
- Partner with deep learning engineers, platform teams, and GPU architects to validate improvements.
- Communicate performance findings, tradeoffs, and recommendations to influence system and software design decisions.
Requirements
- Bachelor's degree or higher in computer science, computer engineering, or a related field, or equivalent experience.
- 12+ years of experience and strong programming skills in C++ and Python.
- Experience with performance engineering, benchmarking, profiling, and optimization of complex software or systems.
- Solid foundation in operating systems, computer architecture, and distributed systems.
- Ability to communicate technical findings, prioritize high-impact work, and build alignment across teams.
- Experience with large-scale AI clusters or distributed training and inference workloads is preferred.
- Experience with CUDA, GPU computing systems, GPU performance analysis, PyTorch, or JAX/XLA is preferred.
About Nvidia
Since its founding in 1993, NVIDIA (NASDAQ: NVDA) has been a pioneer in accelerated computing. The company’s invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined computer graphics, ignited the era of modern AI and is fueling the creation of the metaverse. NVIDIA is now a full-stack computing company with data-center-scale offerings that are reshaping industry.