AI Accelerator LLVM Compiler Engineer

Meta; Bellevue (WA); Híbrido; USD 140.000 - 200.000; Jornada completa

Descripción de la vacante

Meta in Bellevue, WA is looking for a Software Engineer to join the MTIA LLVM Compiler team, contributing to the compiler toolchain for Meta's custom silicon AI accelerators. The role spans designing and implementing production compiler stacks for PyTorch model compilation through LLVM-based intermediate representations to optimized binaries for accelerator blocks.

You will collaborate with compiler, machine learning, firmware, and ASIC experts, review code, profile performance, and help scale

Responsabilidades

• Design, implement, and optimize LLVM-based code generation targeting Meta's custom machine learning accelerators.
• Apply compiler techniques (JIT compilation, dynamic code generation, optimization passes) to build high-performance simulation infrastructure for accelerator hardware.
• Develop and enhance compiler passes, optimizations, and transformations within the LLVM/MLIR infrastructure to improve performance, correctness, and compilation speed.
• Contribute to the development of intermediate representations, compiler libraries, and analysis tools in the LLVM/MLIR ecosystem.
• Conduct design and code reviews; evaluate generated code quality, debug, diagnose, and drive resolution of compiler and cross-disciplinary system issues.
• Analyze and improve the efficiency, scalability, and stability of the compiler toolchain.
• Interface with other compiler-focused teams (both internal and open-source LLVM community) to evaluate and incorporate innovations.
• Mentor other engineers on compiler engineering best practices and improving engineering quality across the team.

Descripción del empleo

Meta in Bellevue, WA is looking for a Software Engineer to join the MTIA LLVM Compiler team, contributing to the compiler toolchain for Meta's custom silicon AI accelerators. The role spans designing and implementing production compiler stacks for PyTorch model compilation through LLVM-based intermediate representations to optimized binaries for accelerator blocks.

You will collaborate with compiler, machine learning, firmware, and ASIC experts, review code, profile performance, and help scale