Compiler Engineer - AI Inference

at Nvidia

📍 Santa Clara, United States

USD 152,000-241,500 per year

MIDDLE

✅ 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 @ 3 Communication @ 6 Debugging @ 8 GPU @ 3 LLM @ 6 Performance Analysis @ 8 Python @ 8

Details

NVIDIA is seeking top-tier AI Compiler Engineers to drive innovation within its compiler organization. In this role, you will push the boundaries of what is possible in AI performance and help build the technology that powers the next generation of computing.

Responsibilities

Drive technical innovation: Participate in hands-on development focusing on kernel generation and computational graph optimizations for next-generation NVIDIA GPUs.
Advance the state-of-the-art: Solve complex compilation problems for AI workloads (both inference and training) and transition these breakthroughs into enterprise and consumer products.
Collaborate on hardware/software co-design: Partner with experts across software, hardware, and research divisions to architect and co-design future silicon.
Scale AI to the datacenter: Participate in the advancement and optimization of datacenter-scale AI workload deployments.

Requirements

BS or MS in Computer Science, Computer Engineering, or a related field (or equivalent experience); a PhD is strongly preferred.
Compiler Experience: 3+ years of relevant industry experience specializing in compiler optimizations, synthesis, and placement.
MLIR Knowledge: Hands-on experience working with MLIR.
Programming Excellence: Exceptional C/C++ and Python programming and software design skills, including rigorous debugging, performance analysis, and test design.
Team Dynamics: Strong communication and interpersonal skills, able to collaborate effectively in a dynamic, fast-paced, and product-oriented environment.

Ways to stand out from the crowd

Hardware Implementation: Hands-on experience implementing complex AI workloads on CPU, GPU, and/or custom AI accelerator architectures.
LLM Knowledge: Deep understanding of Large Language Model (LLM) inference and its implications for computer architecture.
Architecture & Design: Demonstrated understanding in designing and architecting comprehensive compiler frameworks from the ground up.

NVIDIA notes that the base salary range is determined based on location and experience, and the posting specifies a base salary range.

Applications for this job will be accepted at least until April 28, 2026.