Software Engineer, Systems ML - Compilers / Backend

Job Title

Software Engineer, Systems ML - Compilers / Backend

Role Summary

Build and maintain a compiler toolchain that compiles PyTorch models to binaries for custom ML accelerator hardware used in AR/VR systems. Work on compiler passes, code generation, and cross-disciplinary co-design with hardware architects, firmware, and ML algorithm teams.

Experience Level

Mid-level. Preferred: 1+ years of experience developing compilers or similar code-optimization software; otherwise typical mid-career software engineering experience in systems or ML infrastructure.

Responsibilities

Design and implement compiler components and support end-to-end toolchain delivery.

• Design and implement compiler passes, optimizations, and backend code generation for ML accelerators.
• Collaborate with ML researchers to map models and dataflows to hardware, estimate performance and power trade-offs.
• Co-design hardware features with architects to improve performance and programmability.
• Develop and maintain ML libraries, intermediate representations, export formats, and analysis tools.
• Optimize kernels, runtimes, and toolchain scalability and stability for on-device inference.
• Perform design and code reviews; profile, debug, and resolve compiler and system issues.
• Coordinate with other compiler teams to evaluate and adopt innovations.

Requirements

Must-have technical skills and employment requirements; preferred items listed separately.

• Proficient 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).
• Strong software design and engineering fundamentals; ability to diagnose and resolve system-level issues.
• Must obtain work authorization in the country of employment at time of hire and maintain it throughout employment.

Nice-to-have / preferred:

• Experience developing or contributing to compiler toolchains (e.g., LLVM, MLIR, GCC, Glow) or backend machine-code generation for on-device inference.
• Experience developing high-performance kernels or runtime components and tuning them for inference accelerators.
• Familiarity with mainstream ML frameworks (PyTorch, TensorFlow) and deep learning techniques.
• Experience working cross-functionally and with responsible/ethical AI practices.

Education Requirements

Bachelor's degree in Computer Science, Computer Engineering, or a relevant technical field, or equivalent practical experience. Degree must be completed prior to joining Meta.

About the Company

Company: Meta Platforms

Headquarters: Menlo Park, California, United States

American technology company that develops social networking products (Facebook, Instagram, WhatsApp) and invests in virtual/augmented reality hardware and software through Reality Labs, focusing on connectivity, advertising, and immersive computing experiences.