Software Engineer, LLVM Compiler

Meta Careers; Bellevue, Northern (WA, KY); Hybrid; USD 140,000 - 200,000; Full time

Job summary

Meta Platforms seeks a Software Engineer to join the MTIA LLVM Compiler team in Bellevue, WA, building a production compiler stack for custom AI accelerators. You will shape compiler passes, transform LLVM IR, and ensure correct, high-performance code across PyTorch models to optimized binaries for hardware backends.

You will work with compiler, ML, firmware, and ASIC experts to balance compile time, runtime performance, and code size while iterating on validation and benchmarking across

Qualifications

• Experience designing and implementing compiler passes.
• Ability to map ML workloads to hardware backends.
• Strong debugging and performance profiling skills.

Responsibilities

• Design and implement LLVM compiler passes for ML accelerator backends.
• Analyze and improve code quality with profiling and benchmarking.
• Develop LLVM IR transformations for efficient mapping to hardware.
• Collaborate with hardware and ML framework teams to ensure correctness.

Skills

LLVM compiler

Optimization

Code generation

IR transformations

Tools

LLVM

Profiling tools

Job description

# Software Engineer, LLVM CompilerBellevue, WA+2 locationsEngineering+ 2 moreApply nowWe 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.---## Software Engineer, LLVM Compiler Responsibilities* Design and implement LLVM compiler passes, including optimization, lowering, and code generation stages targeting ML accelerator backends* Analyze and improve compiler-generated code quality through profiling, benchmarking, and performance instrumentation across ML workloads* Develop and maintain LLVM IR transformations that enable efficient mapping of ML computation graphs to hardware execution units* Collaborate with hardware architecture and ML framework teams to define compiler interfaces and ensure correctness of generated code on custom silicon targets* Identify and resolve correctness and performance regressions through systematic debugging, root cause analysis, and targeted fixes in the compiler pipeline* Own the technical design of compiler components, evaluating trade-offs between compilation time, runtime performance, and code size for ML inference and training workloads* Build and improve automated testing frameworks and benchmarking infrastructure to validate compiler correctness and track performance across hardware generations