AIML - Sr Applied AI Scientist - GenAI Model Autograding, Evaluation
Core
Design and advance state-of-the-art autograder systems to evaluate the quality, performance, and safety of Apple's internal GenAI products at scale.
Role type
Senior Applied AI Scientist (GenAI Evaluation)
Builds
Robust, trustworthy, and extensible autograders for GenAI product assessment
Domain
Generative AI, Large Language Models, AI Evaluation
Deliverable
production ML models
Required skills
Prompt engineering, Foundation model adaptation, GenAI model building, LLMOps, Analytical judgment, Data quality assessment
Preferred skills
Automated feedback generation, Human annotation operations, Human-in-the-loop workflows, Image quality evaluation
Technologies
GenAI models, LLMOps tools
Responsibilities
Design autograder systems, Adapt foundation models for evaluation, Collaborate on deployment with product and engineering teams, Diagnose autograder limitations and biases
Seniority
Senior, hands-on IC
