Drimva

Meta

Software Engineer, LLVM Compiler

$154K–$217K

Bellevue, WA +2 · Full-time · Posted Sep 5, 2026

Location
Bellevue, WA
Menlo Park, CA
New York, NY
Experience
5+ years developing compilers or code optimization software, with demonstrated technical leadership.
Education
Bachelor’s degree in Computer Science, Computer Engineering, a relevant technical field, or equivalent practical experience.

About the job

Develop and optimize an LLVM-based compiler stack that translates PyTorch and other ML workloads into efficient binaries for Meta’s custom AI accelerators.

What you'll do

  • Design and implement compiler passes and LLVM IR transformations for ML accelerator backends.
  • Profile, benchmark, debug, and improve compiler correctness and generated-code performance.
  • Collaborate across hardware, ML, and framework teams to design compiler components and deliver system-level optimizations.

What they ask for

  • Bachelor’s degree in Computer Science, Computer Engineering, a relevant technical field, or equivalent practical experience.
  • Proficiency in C++ or Rust and experience with large-scale software development, debugging, testing, and performance analysis.
  • Experience with LLVM/MLIR or a comparable production compiler codebase, and a track record delivering compiler features or optimization passes.
  • Experience driving cross-team technical initiatives, working across hardware and ML boundaries, and mentoring engineers.

Nice to have

  • Experience with AI framework development or accelerating deep-learning models on hardware; familiarity with PyTorch, TensorFlow, or MLIR-based toolchains.
  • Experience contributing to LLVM/MLIR, upstream compiler projects, hardware-specific optimization, or AI-assisted workflow improvements.

Pay

$154,003/year to $217,000/year + bonus + equity

Tools

LLVM, MLIR, C++, Rust, GCC, MSVC, PyTorch, TensorFlow

AI focus

Build compiler technology for deep-learning workloads on custom AI accelerators; the posting also asks for ongoing AI skill development and use of AI tools to improve workflows.

Model-written summary · the original posting is authoritative

First seen Oct 15, 2026 · Last verified Nov 4, 2026 (UTC)