Are you passionate about exploring computer architectures for AI? Do you like to build the industry leading product at the intersection of hardware and software? We are seeking world-class programmers and performance architects who love to squeeze out every cycle of performance from deep learning codes. In this role, you will craft and maintain a library that ships our best-performing GPU kernels to NVIDIA's industry-leading AI products. This position in our team offers the opportunity to have real impact in a fast-moving, technology-focused company.

What you'll be doing:

• Design and develop the architecture, interface and features of the GPU kernel library

• Keep improving the quality and performance of the library and its GPU kernels

• Explore and expand the boundary of innovative technologies like GPU code generation and fusion

• Contribute to NVIDIA's AI business by collaborating closely with DL product teams as well as kernel development teams

What we need to see:

• MS, PhD or equivalent in relevant fields (CS, EE, Math)

• 2+ years of relevant work or research experience

• Strong programming skills in C, C++, and Python

• Excellent problem solving skills and learning capability

• Experience with designing software architecture, interfaces, and building testing infrastructures

• Good communication and a great teammate

Ways to stand out from the crowd:

• Familiar with CUDA programming and GPU architecture

• Background with DL fundamentals, frameworks, graph compilers, LLVM, MLIR etc.

• Hands-on experience in development on Linux and Windows platforms, C++ build tools like CMake and DevOps tools, including Docker, Jenkins, Kubernetes etc.

• Track record of mentoring junior engineers and leading a project and a team