Senior Compiler Engineer - Backend GPU

at Nvidia

📍 Santa Clara, United States

USD 152,000-241,500 per year

SENIOR

✅ On-site

Tech Stack
Tag name is followed by "@" symbol and proficiency level value. About proficiency levels:

1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;

3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;

7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;

10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.

AI CUDA @ 4 Communication @ 6 GPU @ 4 LLVM @ 4 OpenCL OpenGL @ 4 Performance Analysis @ 6

Details

NVIDIA is searching for a Senior Backend Compiler Engineer with experience in LLVM code generation to join its GPU Software organization. The Compiler team constructs and emits high-performance GPU machine instructions for Graphics (OpenGL, Vulkan, DirectX) and Compute (CUDA, PTX, OpenCL, Fortran, and C++), supporting NVIDIA's current and future complex parallel SIMT architectures.

Responsibilities

Guide the design and implementation of a new LLVM-based backend JIT compiler targeting NVIDIA GPUs.
Design and develop compiler passes and optimizations to meet high-performance and low compilation-time requirements.
Work with global compiler, hardware, and application teams to oversee improvements and resolve problems.
Apply and adapt the latest compiler technologies to produce premier, robust, and supportable compilers and tools.
Influence and work on new GPU architectures.

Requirements

Bachelor's degree or higher in Computer Science, Computer Engineering, or equivalent experience.
At least 4 years of compiler development experience, including at least 3 years of LLVM experience focused on code generation.
Expertise in LLVM code generation, including instruction scheduling, software pipelining, register allocation, GlobalISel, TableGen, LLVM IR, and Machine IR (MIR).
Proficiency in compiler design and performance analysis tools.
Excellent hands-on C++ programming skills applied to industry-standard C++ compilers and development frameworks.
Strong software engineering background, with a focus on crafting robust and maintainable solutions to challenging problems.
Good communication and documentation skills; self-motivated.

Preferred Qualifications

Master's degree or PhD, with at least 5 years of relevant experience.
Experience developing compiler optimizations and code generation for GPUs.
Experience developing CUDA, DirectX, or OpenGL/Vulkan applications.
Strong interpersonal skills and the ability to lead and influence others in the department.

Benefits

Competitive salary.
Equity and benefits.
NVIDIA is an equal opportunity employer committed to fostering a diverse work environment.

Applications for this job will be accepted at least until March 3, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes.