Systems ML & Compiler Engineer for On-Device AI (AR/VR)

Meta; Redmond (WA); On-site; USD 154,000 - 217,000; Full time

Job summary

Meta’s Reality Labs Silicon team seeks a Software Engineer to develop a clean slate compiler for state-of-the-art deep learning hardware components optimized for AR/VR systems. You will design, implement, and optimize the compiler toolchain to translate PyTorch models into binaries for custom accelerator blocks.

The role involves collaborating with compiler, ML, software, firmware, and ASIC experts to ensure high performance, power efficiency, and on-device AI capabilities.

Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, or equivalent practical experience.
• 2+ years experience developing compilers, toolchains, runtime, or similar code optimization software.
• Experience in Python and/or C/C++ for development, debugging, testing and performance analysis.
• Experience in AI framework development or accelerating models on hardware architectures (GPU, TPU, custom AI ASICs).

Responsibilities

• Analyze and design effective compiler passes and optimizations; implement and/or enhance code generation targeting ML accelerators.
• Collaborate with algorithm research teams to map ML graphs to hardware implementations; analyze data flows and silicon power/performance.
• Coordinate with hardware architects to co-design features maximizing performance, power efficiency and programmability.
• Contribute to ML libraries, IRs, export formats, and analysis tools.
• Improve toolchain efficiency, scalability, and stability; optimize kernels and compiled code for ML inference latency.
• Conduct design and code reviews; diagnose and resolve compiler and cross-disciplinary issues.

Skills

Compilers

Python

C/C++

Machine Learning

PyTorch

Education

Bachelor's degree in Computer Science/Engineering

Tools

MLIR

LLVM

GCC

MSVC

Job description

Meta’s Reality Labs Silicon team seeks a Software Engineer to develop a clean slate compiler for state-of-the-art deep learning hardware components optimized for AR/VR systems. You will design, implement, and optimize the compiler toolchain to translate PyTorch models into binaries for custom accelerator blocks.

The role involves collaborating with compiler, ML, software, firmware, and ASIC experts to ensure high performance, power efficiency, and on-device AI capabilities.