Senior Compiler Optimization Engineer, LLVM - MLIR

at Nvidia
📍 Redmond, United States
USD 148,000-287,500 per year
SENIOR
✅ On-site

SCRAPED

Used Tools & Technologies

Not specified

Required Skills & Competences ?

Communication @ 4 Parallel Programming @ 4 CUDA @ 4 GPU @ 1

Details

We are looking for an experienced Compiler Optimization Engineer to join a Compute Compiler Team focused on delivering features and improvements to CUDA and other compute compilers to realize the potential of NVIDIA GPUs for workloads such as deep learning, scientific computation, and autonomous vehicles. The team works on core compiler components that accelerate general-purpose computation on GPUs and collaborates across compiler, hardware, and application teams.

Responsibilities

  • Analyze performance of application code running on NVIDIA GPUs using profiling tools.
  • Identify opportunities for performance improvements in the LLVM-based compiler middle-end optimizer.
  • Design and implement new compiler passes and optimizations to produce robust, maintainable compiler and tooling.
  • Interact with the open-source LLVM community to ensure tighter integration.
  • Collaborate with architecture teams to influence hardware evolution and features.
  • Work with geographically distributed compiler, hardware, and application teams to oversee improvements and resolve problems.
  • Contribute to deep-learning compiler technology spanning architecture design and higher-level language support.

Requirements

  • B.S., M.S., or Ph.D. in Computer Science, Computer Engineering, or related fields (or equivalent experience).
  • 5+ years of experience in compiler optimizations, including loop optimizations, inter-procedural optimizations, and global optimizations.
  • Excellent hands-on C++ programming skills.
  • Understanding of processor ISAs; GPU ISA experience is a plus.
  • Strong software engineering principles with emphasis on robust and maintainable solutions.
  • Good communication, documentation skills, and self-motivation.

Preferred / Ways to stand out

  • Masters or PhD preferred.
  • Experience developing applications in CUDA or other parallel programming languages.
  • Deep understanding of parallel programming concepts.
  • Experience in LLVM, MLIR, and/or Clang compiler development.
  • Familiarity with deep learning frameworks and NVIDIA GPUs.

Benefits and Compensation

  • Base salary range (depending on level and location):
    • Level 3: 148,000 USD — 235,750 USD
    • Level 4: 184,000 USD — 287,500 USD
  • Eligibility for equity and benefits. More information: https://www.nvidia.com/en-us/benefits/

Other Information

  • Location: Redmond, Washington, United States.
  • Employment type: Full time.
  • Applications accepted at least until August 3, 2025.
  • NVIDIA is an equal opportunity employer committed to fostering a diverse work environment.