On-device ML Infrastructure Engineer, Compiler & Runtime, Graphics, Games & ML

Apple Apple · Big Tech · Cupertino, CA · Machine Learning and AI

Seeking an experienced ML Infrastructure Engineer to build and optimize the execution engine and compilation toolchain for on-device ML models on Apple products. This role focuses on creating efficient, portable, and extensible runtimes and compilers, connecting compiler technology, runtime components, kernel libraries, and hardware compilers to enable ML execution across various devices.

What you'd actually do

  1. Help lead and deliver on critical initiatives for on device machine learning infrastructure.
  2. Design, build, and maintain critical machine learning infrastructure that powers Apple’s machine learning features.
  3. Collaborate with downstream hardware compilers to best leverage Apple’s machine learning hardware.
  4. Collaborate with first and third party users to adopt our infrastructure and apply protocols when they implement machine learning on Apple devices.
  5. Ensure our infrastructure can run optimally for a wide range of first and third party machine learning models.

Skills

Required

  • Bachelors in Computer Science, Engineering, or related subject area and 5+ years of hands on experience.
  • Highly proficient in C++.
  • Familiarity with Python and Swift.
  • Familiarity with Operating Systems and Embedded Programming.
  • Sound understanding of ML fundamentals, including common architectures such as Transformers.
  • Good communication skills, including ability to communicate with multi-functional audiences.

Nice to have

  • Experience with any on-device ML stack, such as TFLite, ONNX, ExecuTorch, etc.
  • Experience with open source machine learning models (Mistral, Phi, Gemma, Huggingface, etc)
  • Experience with any compiler stack (MLIR/LLVM/TVM/...).
  • Experience with any ML authoring framework (PyTorch, TensorFlow, JAX, etc.).
  • Experience with machine learning accelerators and GPU programming.

What the JD emphasized

  • critical initiatives
  • critical machine learning infrastructure
  • make critical decisions

Other signals

  • on-device ML infrastructure
  • ML compilers and runtimes
  • model compression and acceleration
  • efficient execution on Apple devices