Senior AI Compiler Engineer — CUDA/MLIR Expert (Equity)

NVIDIA; California (MO); On-site; USD 152,000 - 241,500; Full time

Job summary

NVIDIA is hiring an AI & Deep Learning Compiler Engineer to advance the DLC team’s optimizer stack across data centers, devices, and robotics. You will analyze networks, implement compiler techniques for AI workloads, and push for high inference performance and fast build times on NVIDIA GPUs.

The role requires strong C/C++, Python, and experience with compiler technologies. Location-based salary ranges and equity/benefits accompany this existing vacancy.

Qualifications

• Advanced degree or equivalent experience in computer science or related field.
• 3+ years in performance analysis and compiler optimizations.
• Strong C/C++ and Python programming and debugging skills.
• Experience with compiler tech (MLIR/LLVM/XLA/Triton).

Responsibilities

• Analyze deep learning networks and develop compiler optimization algorithms.
• Debug performance bottlenecks on NVIDIA GPUs using CUDA.
• Define APIs, optimize performance, and implement AI workload compiler tech.

Skills

CUDA

C/C++

Python

Performance analysis

Compiler optimizations

Education

Bachelor's or higher in CS/CE

PhD preferred

Tools

MLIR

LLVM

XLA

Triton

Job description

NVIDIA is hiring an AI & Deep Learning Compiler Engineer to advance the DLC team’s optimizer stack across data centers, devices, and robotics. You will analyze networks, implement compiler techniques for AI workloads, and push for high inference performance and fast build times on NVIDIA GPUs.

The role requires strong C/C++, Python, and experience with compiler technologies. Location-based salary ranges and equity/benefits accompany this existing vacancy.