Software Engineer, Systems ML - Compilers / Backend

Meta Meta · Big Tech · Sunnyvale, CA

Software Engineer focused on developing and optimizing compiler toolchains for custom AI hardware accelerators in AR/VR systems. The role involves analyzing and implementing compiler passes, code generation for ML accelerators, mapping ML graphs to hardware, and optimizing compiled code for low-latency ML inference.

What you'd actually do

  1. Analyze and design effective compiler passes and optimizations.
  2. Implement and/or enhance code generation targeting machine learning accelerators
  3. Work with algorithm research teams to map ML graphs to hardware implementations, model data-flows, create cost-benefit analysis and estimate silicon power and performance
  4. Work with hardware architects to co-design hardware features that maximize performance, power efficiency and programmability
  5. Contribute to the development of machine-learning libraries, intermediate representations, export formats, and analysis tools

Skills

Required

  • Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
  • 2+ years experience developing compilers, toolchains, runtime, or similar code optimization software
  • Experience in software design and programming 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)
  • Experience of developing in a mainstream machine-learning framework, e.g. PyTorch, MLIR, Tensorflow or Caffe
  • Experience with machine-code generation or compiler back-ends for on-device inference workloads
  • Experience working and communicating cross functionally in a team environment
  • Experience working on and contributing to an active compiler toolchain codebase, such as LLVM, MLIR, GCC, MSVC, Glow
  • Experience in deep learning algorithms and techniques, e.g., convolutional neural networks, recurrent networks, etc
  • Experience developing high-performance kernels or runtime components and tuning them for inference specific accelerator platforms

Nice to have

  • Demonstrated ongoing AI skill development (e.g., prompt/context engineering, agent orchestration) and staying current with emerging AI technologies
  • Experience adhering to and implementing responsible, ethical AI practices (e.g., risk assessment, bias mitigation, quality and accuracy reviews)
  • Demonstrated ability to integrate AI tools to optimize/redesign workflows and drive measurable impact (e.g., efficiency gains, quality improvements)

What the JD emphasized

  • custom silicon
  • compiler tool-chain
  • machine learning accelerators
  • ML inference
  • PyTorch
  • custom hardware accelerator blocks
  • latency targets

Other signals

  • custom silicon for AI devices
  • compiler tool-chain for deep learning hardware
  • compiling PyTorch models down to binaries for custom hardware accelerator blocks
  • ML inference latency targets