Software Engineer, LLVM Compiler

We are seeking a software engineer to join the MTIA LLVM Compiler team, working on the compiler toolchain for Meta's custom silicon AI accelerators. You will be part of our efforts to architect, design, and implement a production compiler stack targeting next-generation deep learning hardware. The team includes compiler, machine learning, firmware, and ASIC experts, and the work spans from compiling PyTorch models through LLVM-based intermediate representations down to optimized binaries for hardware accelerator blocks.

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