Compiler Engineer, LLVM

Nvidia•Santa Clara, CA

42d

About The Position

We are looking for an enthusiastic LLVM Compiler Engineer for an exciting and fun role in our GPU Software organization. We deliver features and improvements to better realize the potential of NVIDIA GPUs for a growing range of computational workloads, ranging from deep learning, scientific computation, and self-driving cars to graphics workloads for AAA game titles on gaming platforms. Our compiler organization makes its mark on every GPU NVIDIA produces. Would you like to add this to your accomplishments? If you have prior experience working with shaders or shader compilers for languages like GLSL, HLSL, SLANG, that's a big plus! We need you as a key member of a small team that is working on a core compiler component for our graphics drivers as well as for accelerating general purpose computation on the GPU. You will be solving critical problems working alongside some of the top valued diverse minds in GPU computing and systems software, doing what you enjoy. If this sounds like a fun challenge, we want to hear from you!

Requirements

BS/MS in Computer Science or Computer Engineering (PhD strongly preferred) or equivalent experience.
2+ years of experience and strong background in compilers.
You would need strong C/C++ programming skills, as well as a deep understanding of parallel programming models.
Experience with compiler optimizations, especially working with LLVM infrastructure.

Nice To Haves

Experience developing CUDA, DirectX, OpenGL/Vulkan applications.
Background with developing compiler optimizations and code generation for GPUs.
Ability to do code generation and building a good compiler framework.
Collaborate well with others in an energizing environment.
You should have strong interpersonal skills and influence others in the department.

Responsibilities

Work on design and implementation of significant parts of the graphics' compiler (SPIR-V and DXIL compiler)
Work on performance analysis and design/implementation of new optimizations.
Partner with global compiler, GPU driver, architecture, and application teams to coordinate improvements and problem resolutions.
Seek interesting and meaningful compilation problems for state-of-the-art GPU technologies.
Contribute to open-source projects (GLSLANG, LLVM, DXC - HLSL compiler).