ML Compiler Architect for Edge AI Accelerators

Meta; New York (NY); On-site; USD 184,000 - 257,000; Full time

Benefits offered by this job

Bonus

Equity

Benefits

Job summary

Meta Reality Labs seeks a Software Engineer, Systems ML - Compilers to lead ML compiler infrastructure for AR/VR accelerators. You will optimize PyTorch models for custom silicon, work with LLVM/MLIR toolchains, and collaborate with hardware teams to maximize performance and efficiency on edge devices.

You will design IRs, optimization passes, and code generation, mentor engineers, and interface with other compiler teams to push innovations in compiler technology for Meta's on-device AI stack.

Qualifications

• Bachelor's degree in CS/CE or equivalent practical experience.
• 3+ years of experience developing compilers, toolchains, or code optimization software.
• Experience with LLVM, MLIR, or similar compiler infrastructure frameworks.
• Experience with GPUs/TPUs or custom AI accelerators.
• C++ for compiler and systems‑level programming.
• Experience leading end-to-end compiler initiatives across teams.

Responsibilities

• Lead architecture and implementation of ML compiler infrastructure, including IR, optimization passes, and code generation for custom accelerators.
• Design and implement compiler transformations for GPU/TPU/edge AI accelerators.
• Develop LLVM/MLIR‑based toolchains for PyTorch models to optimized binaries.
• Collaborate with hardware teams to maximize performance and power efficiency for edge devices.
• Analyze and improve scalability, stability, and extensibility of compiler toolchains.
• Mentor engineers on compiler design patterns and review code.

Skills

C++

Compiler design

LLVM/MLIR

PyTorch

Edge AI

Performance optimization

Education

Bachelor's degree in CS/CE or equivalent

Tools

LLVM

MLIR

PyTorch

TensorFlow

Job description

Meta Reality Labs seeks a Software Engineer, Systems ML - Compilers to lead ML compiler infrastructure for AR/VR accelerators. You will optimize PyTorch models for custom silicon, work with LLVM/MLIR toolchains, and collaborate with hardware teams to maximize performance and efficiency on edge devices.

You will design IRs, optimization passes, and code generation, mentor engineers, and interface with other compiler teams to push innovations in compiler technology for Meta's on-device AI stack.