Senior AI Compiler Engineer — Equity Eligible, CUDA/MLIR

NVIDIA Gruppe; Santa Clara (CA); On-site; USD 183,000 - 210,000; Full time

Job summary

NVIDIA is seeking an AI & Deep Learning Compiler Engineer in Santa Clara, California. You will analyze deep learning networks, develop compiler optimization algorithms, and optimize CUDA performance on NVIDIA GPUs, contributing to the DLC across data centers, devices, and robotics.

The role requires strong C/C++ and Python, experience with MLIR/LLVM/XLA/Triton, and the ability to lead development efforts in a collaborative, fast-paced team environment.

Qualifications

• Bachelor’s, master’s or Ph.D. in CS/CE or equivalent experience.
• 3+ years of performance analysis and compiler optimizations experience.
• Experience with compiler technologies such as MLIR, LLVM, XLA, Triton.
• Excellent C/C++ and Python programming, debugging, and test design.
• Ability to work independently and lead development efforts.
• Strong interpersonal skills in a dynamic, product-focused team.

Responsibilities

• Analyzing deep learning networks and developing compiler optimization algorithms.
• Strong programming in CUDA, analyzing and debugging performance bottlenecks on GPUs.
• Define public APIs, optimize performance, and craft compiler techniques for AI workloads and future NVIDIA GPUs.

Skills

C/C++

Python

Performance analysis

Leadership

Education

Bachelor’s/Master’s/PhD in CS/CE

Tools

MLIR

LLVM

XLA

Triton

Job description

NVIDIA is seeking an AI & Deep Learning Compiler Engineer in Santa Clara, California. You will analyze deep learning networks, develop compiler optimization algorithms, and optimize CUDA performance on NVIDIA GPUs, contributing to the DLC across data centers, devices, and robotics.

The role requires strong C/C++ and Python, experience with MLIR/LLVM/XLA/Triton, and the ability to lead development efforts in a collaborative, fast-paced team environment.