The On-Device Query Understanding team builds personalized, state-of-the-art query understanding models that power search intelligence across Spotlight and first-party apps like Mail, Photos, and Reminders. In this role, you will incorporate cutting-edge research in Large Language Models (LLMs), Natural Language Understanding (NLU), and machine learning inference optimization to deliver fast, power-efficient ML solutions to complex query understanding problems. You will bridge research and engineering excellence to drive scalable evaluations and on-device modeling improvements, directly impacting millions of Apple users while advancing how Apple understands what people are looking for, and why.

Minimum Qualifications
4 or more years of experience in machine learning, natural language processing, or computer vision, applied at scale
Production software engineering experience with Python, Go, C/C++, Swift, or Objective-C
Strong communication and collaboration skills
Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, Statistics, Physics, Mathematics, or a related field

Preferred Qualifications
Advanced degree (Master's or Ph.D.) in Computer Science, Statistics, or a related field, or equivalent industry experience
Experience with Small Language Models (SLMs) and on-device LLM training, model compression/quantization, and deployment to production
Experience in large-scale query understanding, search, recommendation, or personal assistant systems
Proficiency with machine learning frameworks such as PyTorch, JAX, TensorFlow, or XGBoost
Background in personalization and data-driven decision making, with the ability to prototype solutions and conduct critical analysis
Experience with Swift, Swift frameworks, or Apple platform development is a plus
Experience with build infrastructure, release management, and CI/CD pipelines is a plus