Apple · Cupertino

On-device ML Infrastructure Engineer (Fine-tuning and Customization)

(f/m/d) · 3/18/2025

Description

We are building an end-to-end developer experience for ML development that, by taking advantage of Apple’s vertical integration, allows developers to iterate on model authoring, optimization, transformation, execution, debugging, profiling and analysis. This role focuses on the Create ML framework for machine learning model and Apple Intelligence customization. We’re looking for a highly motivated software engineer that is creative, talented, and passionate about providing high quality developer tools, workflows and APIs in the fast paced and dynamic space of ML. Key responsibilities: Designing and implementing workflows for fine-tuning and adapting ML models Architecting and maintaining the internals of the Create ML framework Working with internal and external developers to enable their uses cases powered by on-device ML Triaging and addressing framework performance issues and functionality gaps

Qualifications

  • Strong and proven software development skills. Proficiency in Swift is a plus.
  • Experience working on machine learning projects, such as model training, evaluation, inference and on-device optimization.
  • Passion for software architecture, data structures and processes
  • Bachelor of Science in Computer Science or Electrical Engineering

Preferred Qualifications

  • Experience with on-device ML frameworks (Core ML, Win ML, ONNX, TF Lite or ExecuTorch)
  • Knowledge of general ML Framework implementation (Jax, PyTorch, or TensorFlow)
  • Past experience in using Apple’s ML frameworks and libraries is a plus.
  • MS/PhD in Computer Science or Electrical Engineering
  • Excellent communication skills that can help others understand code/problems/ideas

Benefits

Application

View listing at origin and apply!