Jobs / App***

On-device ML Infrastructure Engineer (Orchestration & Performance)

App*** · Cupertino, CA, United States
Visa sponsorship details are locked. Unlock company name and apply link with .
Cupertino, CA, United StatesExp: 3-5 yrs150,400-277,600 USD/yearlyOnsite
Remuneration
150,400-277,600 USD/yearly
Location
Cupertino, CA, United States
Visa sponsorship
Sponsors visa

Job summary

The On-Device Machine Learning Infrastructure Engineer role focuses on developing the infrastructure necessary for efficient machine learning execution across App*** devices. Key responsibilities include implementing full-stack changes for deploying state-of-the-art models, collaborating with various teams for advanced applications, and optimizing model orchestration on App*** Silicon hardware.

Benefits

Comprehensive medical and dental coverageRetirement benefitsDiscounted products and free servicesReimbursement for educational expensesDiscretionary bonusesEquity

Qualifications

  • Experience with MLIR-based compilers.
  • Familiarity with deploying applications on App*** platforms.
  • Knowledge of programming paradigms for GPU, CPU, and Neural Engine.
  • Experience writing kernels for ML model execution.
  • 3-5 years of experience with tooling in Python 3 and C++/Swift.
  • Familiarity with common ML model architectures and execution schemes.
  • Experience with PyTorch or related training frameworks.

Responsibilities

  • Drive full-stack changes through the OS and tooling for deploying large SOTA models across the App*** Silicon ecosystem.
  • Partner with teams to support advanced use cases for Siri, App*** Intelligence, Camera, and more.
  • Make changes in the authoring and MLIR-based compiler for state-of-the-art model execution.
  • Implement mechanisms for efficient orchestration of models across App*** Silicon hardware.

Skills

C++MakePython

Relocation

No