GPU Backend Compiler Engineer — LLVM/C++ Expert

NVIDIA; California (MO); On-site; USD 152,000 - 242,000; Full time

Benefits offered by this job

Equity compensation

Benefits

Job summary

NVIDIA is seeking a Backend Compiler Engineer for its GPU Software organization. You will understand, modify, and improve a proprietary GPU compiler backend written in C++, contributing to high-performance code generation for graphics and compute workloads.

You'll design and develop new register allocation passes, work with global teams across hardware and software, and help advance deep-learning compiler technology on modern SIMT architectures. Eligible for equity and benefits.

Qualifications

• BS/MS/PhD or equivalent experience; MS/ PhD highly desired.
• 3+ years of compiler code generation experience (preferably with LLVM).
• Proficient hands-on C++ programming skills.
• Strong background in software engineering principles with a focus on robust and maintainable solutions.
• Good communication and documentation skills.

Responsibilities

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

Skills

C++ programming

LLVM

Compiler engineering

Communication skills

Education

BS/MS/PhD in related field

Tools

LLVM toolchain

Job description

NVIDIA is seeking a Backend Compiler Engineer for its GPU Software organization. You will understand, modify, and improve a proprietary GPU compiler backend written in C++, contributing to high-performance code generation for graphics and compute workloads.

You'll design and develop new register allocation passes, work with global teams across hardware and software, and help advance deep-learning compiler technology on modern SIMT architectures. Eligible for equity and benefits.