Data Scientist - Survey Design, Data Annotation, and Machine Learning Evaluation

Apple is where individual imaginations gather together, committing to the values that lead to great work. Every new product we build, service we create, or experience we deliver is the result of us making each other's ideas stronger. The diversity of our people and their thinking inspires the innovation that runs through everything we do. When we bring everybody in, we can do the best work of our lives. Here, you'll do more than join something - you'll add something. The Special Projects team at Apple is developing novel user-facing conversational features that leverage the multimodal capabilities of state-of-the-art foundation models. As part of this process, we generate real-world and simulated data, gather human data annotations, analyze the results, and use them to build and evaluate Large Language Model judges. We are looking for a skilled Data Scientist to join our Machine Learning Evaluations teams. This person will work closely with ML Engineers to manage and analyze our human and automated data annotation processes, and to develop, test, and refine LLM judges for generative AI model evaluation. A successful candidate is experienced in survey design, data annotation, LLM prompt engineering and prompt optimization, and has strong statistical analysis skills.Work closely with ML Engineers to understand data annotation needs Design and manage data annotation processes, including the development of user instructions, annotation pipeline processing, and process improvement Develop LLM auto-judges and judging criteria for generative AI model evaluation Analyze collected data annotations to assess and refine LLM auto-judgesBA or Master's degree in Data Science, Statistics, or a quantitative social science field 2+ years of hands-on experience working in survey design and human data annotation Proficiency in Python Excellent communication skillsPhD in Data Science, Statistics, or a quantitative social science field Hands-on industry experience with product-focused statistical analysis Experience working with large-scale multimodal data and data-annotation pipelines Experience with LLM prompt engineering & prompt optimization Experience with LLM auto-judges for generative AI model evaluation A track record of publications or technical presentations in Data Science or a related field Excellent at cross-functional collaboration