Drimva

Apple

Machine Learning Engineer, Evaluation and Quality, Creativity Apps

$142K–$263K

San Diego Metro Area, California · Full-time · Posted Oct 27, 2026

Experience
5+ years of industry experience in machine learning or software engineering, focused on ML/AI model evaluation and quality.
Education
Bachelor's degree in Computer Science, Data Science, Machine Learning, or a related field, or equivalent experience.

About the job

Own evaluation strategy and end-to-end quality for ML models and AI features in Apple’s Creativity Apps, from datasets and infrastructure to ship/no-ship recommendations.

What you'll do

  • Define evaluation methods, metrics, datasets, and scalable infrastructure for ML models, LLMs, and AI features.
  • Use ML, LLMs, and agentic workflows to automate evaluation, generate tests, and analyze results.
  • Drive feature quality from model checkpoints through shipping, resolve issues, and report quality risks and recommendations.

What they ask for

  • 5+ years of industry experience in machine learning or software engineering focused on ML/AI model evaluation and quality.
  • Experience with evaluation methods, dataset curation and quality, and ML evaluation infrastructure at scale.
  • Strong ML fundamentals and LLM knowledge, including agentic workflows; experience applying LLMs or agentic workflows to evaluation and quality.
  • Proficient in Python and/or Swift or comparable languages; strong communication and cross-functional collaboration skills.

Nice to have

  • Knowledge of software quality assurance, objective image/video quality evaluation, color science, or subjective image/video review.
  • Experience as a creator or familiarity with iOS and macOS.

Pay

$142,300 to $263,300 USD base salary

Tools

Python, Swift, ML, LLMs, agentic workflows, iOS, macOS

AI focus

Evaluate and improve the quality of ML models, LLMs, and AI features; apply LLMs and agentic workflows to automated judging, test generation, and analysis.

Model-written summary · the original posting is authoritative

First seen Oct 28, 2026 · Last verified Nov 4, 2026 (UTC)