Expoint – all jobs in one place
מציאת משרת הייטק בחברות הטובות ביותר מעולם לא הייתה קלה יותר
Limitless High-tech career opportunities - Expoint

Apple On-device ML Performance Infrastructure Engineer 
United States, Washington, Seattle 
1788968

Yesterday
As an engineer in this role, you will be primarily focused on building performance infrastructure to present high level views of ML inference behavior which are created by gathering lower level data from execution delegates and relating the data to the high level model. You’ll work with models created by the most popular ML frameworks (PyTorch, JAX, MLX, etc) and will analyze the execution to ensure the stack achieves full machine performance on Apple Silicon. The role also has exposure to building higher level APIs and toolings to enable developers to visualize, diagnose, and debug correctness and performance issues while onboarding models to on-device deployment.The role requires understanding of ML architectures, compilers, runtimes, system performance, and system software engineering. Key responsibilities:* Build production-critical system software for tracking low level details of executing ML models on Apple Silicon and then associating this with ops from high level models.* Optimize model execution for various system goals such as performance, memory, energy efficiency, etc.* Contribute to maintaining the health and performance of the ML benchmarking service, including debugging failures and addressing user questions / requests.
  • Highly proficient in C++. Familiarity with Python.
  • Familiarity with Operating Systems, embedding programming, parallel programming.
  • Knowledge of ML fundamentals including training regimes, evaluation and deployment/inference.
  • A passion/interest for ML, particularly applied to on-device use cases.
  • Good communication skills, including ability to communicate with cross-functional audiences.
  • Masters or PhDs in Computer Science or relevant disciplines.
  • On-device ML stack, such as TFLite, ONNX, ExecuTorch, etc.
  • ML authoring framework (PyTorch, TensorFlow, JAX, etc.).
  • Compiler stack (MLIR/LLVM/TVM etc.).
  • Accelerators and GPU programming.
  • OS kernel programming, computer architecture or performance analysis
  • Developer tools such as vTune and Nvidia Nsight
  • ML architectures such as Transformers, CNNs or Stable Diffusion a strong plus.
Note: Apple benefit, compensation and employee stock programs are subject to eligibility requirements and other terms of the applicable plan or program.