Apple
Sr. Machine Learning Engineer, ML Systems Evaluation Engineering
$175K–$325K
Cupertino, California +1 · Senior · Full-time · Posted Sep 10, 2026
- Location
- Cupertino, California
Seattle, Washington - Experience
- 7+ years.
- Education
- MS/PhD in Machine Learning or Computer Science, or equivalent experience in a related field.
About the job
Develop offline evaluation systems and datasets to assess Siri and AI/ML models, using LLMs and generative AI to evaluate conversation quality and anticipate edge cases.
What you'll do
- Use LLMs as judges to evaluate model changes and assess the naturalness of assistant conversations.
- Generate adversarial scenarios with generative AI to strengthen evaluation against edge cases.
- Collaborate across teams to curate and evolve evaluation datasets, including for personalized experiences.
What they ask for
- 7+ years applying machine learning to real-world problems and building scalable data solutions for natural language products.
- Experience managing large-scale datasets for ML training and/or evaluation.
- Excellent programming skills in Python.
- MS/PhD in Machine Learning or Computer Science, or equivalent experience in a related field.
Nice to have
- Deep Conversational AI knowledge and understanding of the end-to-end ML product lifecycle.
- Expertise in evaluation coverage for LLMs and agentic systems; large-scale cross-functional ML outcomes; or systems engineering.
Pay
$184,700 and $324,800 USD base salary; $175,000 and $308,500 USD base salary
Tools
Python, Large Language Models (LLMs)
AI focus
Use LLM-as-a-Judge and generative AI for scalable model evaluation, conversation naturalness assessment, and adversarial scenario generation.
Model-written summary · the original posting is authoritative