Senior Deep Learning Profiling Tools Engineer

Details

NVIDIA’s invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined modern computer graphics, and revolutionized parallel computing. More recently, GPU-enabled deep learning ignited modern AI — the next era of computing — with the GPU acting as the workhorse that powers intelligent applications in a multitude of domains and computing environments. With performance at the center of everything we do at NVIDIA, we pride ourselves on not only building the world’s fastest processors, but also on providing a full ecosystem that empowers developers to realize that performance in practice.

NVIDIA’s Deep Learning Architecture and Libraries Group is looking for a software engineer to help us push the boundaries of our performance analysis capabilities. As a member of our team, you will work closely with GPU architects, CUDA developers, and deep learning performance engineers to devise innovative approaches to hardware and software profiling and incorporate them into our internal tools. Your work will accelerate progress toward our broader mission, which spans both hardware and software, to consistently deliver the world’s fastest accelerated computing systems in domains ranging from autonomous vehicles to supercomputers. Join our technically diverse team of GPU architects, software engineers, and infrastructure experts to advance the frontiers of computing performance!

Responsibilities

• Design and develop software tools to profile and analyze AI workloads on NVIDIA systems
• Work with multi-disciplinary teams to design, implement, and verify new features for profiling and monitoring, often incorporating new hardware capabilities
• Define software/hardware metrics for performance analysis of AI workloads and verify them for upcoming architectures
• Constantly learn about the latest techniques and frameworks for training, deploying, and optimizing the performance of AI to improve the efficiency and effectiveness of our tools

Requirements

• Bachelors, Masters, or PhD in relevant field (e.g. CS, EE, CE) or equivalent experience
• 8+ years of relevant experience (including graduate work if applicable)
• Proficiency in C++ and Python.
• Experience with deep learning Frameworks (e.g. PyTorch, JAX, TRT, ONNX, Triton) and strong understanding of deep learning fundamentals
• Strong computer science fundamentals - algorithms, data structures, optimization, debugging, operating systems, and parallel computing

Ways To Stand Out From The Crowd

• Experience with performance analysis of AI training/inference applications
• Knowledge of device drivers and/or compiler implementation
• Knowledge of GPU and/or CPU architecture and general computer architecture principles