GPU Backend Compiler Engineer – Deep Learning Focus

NVIDIA; Oregon (WI); On-site; USD 124,000 - 242,000; Full time

Job summary

NVIDIA's GPU Software division is seeking a Backend Compiler Engineer to help design, modify, and optimize the NVIDIA GPU compiler backend written in C++. You will work on high-performance code paths powering graphics and compute pipelines.

You will collaborate with global teams, contribute new compiler passes, and help drive robust, maintainable solutions across CUDA, OpenGL/Vulkan toolchains and future architectures.

Qualifications

• B.S. or degree in Computer Science/Engineering or equivalent experience
• 2+ years of compiler code generation experience
• Excellent hands-on C++ programming skills
• Strong background in software engineering principles with a focus on crafting robust and maintainable solutions
• Good communication and documentation skills and self-motivated

Responsibilities

• Understand, modify, and improve an NVIDIA proprietary GPU compiler backend written in C++
• Design and develop new compiler passes and optimizations to produce best-in-class, robust, supportable compiler and tools
• Work with global compiler, hardware and application teams to oversee improvements and problem resolutions
• Be part of a team that is at the center of deep-learning compiler technology spanning architecture design and support through functional languages

Skills

C++ programming

Communication skills

Documentation skills

Software engineering principles

Education

B.S. in Computer Science/Engineering

Tools

LLVM

CUDA

DirectX

OpenGL

Vulkan

Machine IR (MIR)

TableGen

Job description

NVIDIA's GPU Software division is seeking a Backend Compiler Engineer to help design, modify, and optimize the NVIDIA GPU compiler backend written in C++. You will work on high-performance code paths powering graphics and compute pipelines.

You will collaborate with global teams, contribute new compiler passes, and help drive robust, maintainable solutions across CUDA, OpenGL/Vulkan toolchains and future architectures.