Job Description

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 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. At NVIDIA, performance is at the core of everything we do. We pride ourselves on not only building the world’s fastest processors, but also on providing a full ecosystem that empowers engineers and developers to realize that performance in practice.
NVIDIA’s GPU Architecture Group is looking for software engineers to help us push the boundaries of our GPU 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 GPU 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!
What you’ll be doing:

• 
  Develop tools to analyze performance of CUDA applications from various sectors (e.g. Deep Learning and scientific computing) on various platforms including embedded systems and large clusters
• 
  Work with multi-disciplinary teams to design, implement, and verify new features for GPU profiling and monitoring, often incorporating new hardware capabilities
• 
  Define performance metrics that will be useful for performance analysis and verify them for upcoming GPU architectures
• 
  Give feedback to improve profiling architecture in GPU
• 
  Constantly learn about the GPU architecture and the performance analysis process to improve the efficiency and effectiveness of our tools

What we need to see:

• 
  Bachelors, Masters, or PhD in relevant field (e.g. CS, EE, CE) or equivalent experience
• 
  5+ years of relevant experience
• 
  Product development experience in C, C++, and Python
• 
  Strong software optimization and debugging skills
• 
  Experience in developing, analyzing, and optimizing parallel algorithms
• 
  In-depth knowledge of GPU and/or CPU architecture and general computer architecture principles

Ways to stand out from the crowd:

• 
  Knowledge of operating systems, device drivers, and/or compiler implementation
• 
  Experience developing CUDA libraries or applications
• 
  Experience analyzing GPU application performance
• 
  Ability to read and write assembly language
• 
  Experience with modern CI/CD tools, including containers

NVIDIA offers competitive pay and benefits, including flexible time off, family leave time, and high-quality medical benefits. We are committed to fostering a diverse work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law. We will provide reasonable accommodations for those who need them to participate in the job application or interview process, to perform essential job functions, or to receive other benefits and privileges of employment.