AIML Applied AI Scientist, Image Autograder Systems, Evaluation

We are looking for an AI Scientist to join a centralized evaluation organization building the next generation of autograders across Apples most visible image generation AI features. nIn this role you will develop autograders that reliably score image output quality at scale. nYour work directly influences the quality of AI experiences used by hundreds of millions of Apple is a high-impact individual contributor role at the intersection of genAI evaluation genAI model training data quality and AI engineering. nYou will work closely with senior AI scientists MLEs data annotation teams and feature engineers in a fast-moving technically rigorous environment.n

In this role you will focus on Autograder research training and with AI feature teams eval design teams and annotation teams to refine feature requirements grading rubrics and gold annotation evaluate and iterate on grading prompts to align autograder behavior with grading rubrics and the gold when prompt tuning reaches its limits and apply other advanced techniques such as fine-tuning to close remaining grading accuracy insightful analysis to measure and explain Autograder with MLEs and feature teams on autograder deployment and scalable system to speed up autograder training

Masters or PhD in Computer Science Machine Learning Artificial Intelligence or a related understanding of visual-language with image quality assessment - perceptual quality dimensions evaluation metrics and rubric in Python; capable of writing well-structured production-ready model communication skills in explaining autograder quality and driving autograder adoption with partner

1 years of industry experience in building VLM-based with autograder and evaluator-specific concepts: grading accuracy agreement with human raters calibration and rubric expertise in prompt tuning and fine tuning for ability to read AI literature and translate it into applied autograder experience in building agentic system to scale autograder training/