Nvidia Distinguished Compiler Engineer - AI 

United States, Texas 

604519780

What you'll be doing:

In this role, you will be leading by hands-on example doing technology development on problems of kernel generation and optimizations for computational graphs for next generation NVIDIA GPUs. The goal of this work will be to advance the state of the art in compilation problem of DL graphs for current and future NVIDIA GPUs and transfer this tech to products. The problems of interest will be drawn from computational graphs as encountered in inference and training workloads. Develop, both, online and offline techniques for use in the production compiler NVIDIA is developing. You will work with experts across software, hardware, and research divisions to co-design the next generation chips.. As part of your role you will also be responsible for technology transfer to production groups.

What we need to see:

• Masters or PhD or equivalent experience in Computer Science, Computer Engineering, or related field.

• 16+ years of relevant work or research experience in compiler optimizations, synthesis, super optimization and computer architecture.

• Be able to work independently, define project goals and scope, and lead your own development efforts

• Excellent programming and software design skills, including debugging, performance analysis, and test design.

• Strong communication skills are required along with the ability to work in a dynamic product-oriented team.

• Experience with the following technologies is a huge plus: OpenAI Triton language and compiler; Deep learning models and algorithms; Polyhedral methods; Program synthesis; Tile based IR and domain specific language; Auto-tuning; Deep learning framework design

Ways to stand out from the crowd:

• Knowledge of CPU and/or GPU architecture. CUDA or OpenCL programming experience desired but not required

• Experience in mentoring early in career engineers and interns is a bonus.