The Applied Sensing & Health team has built innovative ways for users to improve their health, watch for their lives, and get personalized insights from their daily patterns through multimodal sensing and AI models. This team combines advanced machine learning, including integration, adaptation, and tuning of foundation models, with contextual sensing, bolstered by innovative study design, to derive user insights spanning health, fitness, and safety. This has enabled us to deliver meaningful features like Cardio Fitness, Journaling Suggestions, Fall and Crash Detection, and our latest advances to bring our suite of Fitness metrics to AirPods Pro 3, delivering 50 workout types in a single year. We are a dynamic, collaborative group that works at the intersection of scientific research and product development. We develop science-backed designs of best-in-class AI/ML models that capture the multifactorial nature of human health and behavior, delivering insights straight to our customers. We promote innovation and new technology to further improve our creative output. We are seeking a tenacious and passionate person to join this amazing team. If you feel this is you, we'd love to hear from you.

Description

You will help ship interactive features that impact millions of users on a daily basis. You take responsibility; you demonstrate creativity, initiative, and the ability to work to deadlines. You feel a personal stake in the product you ship. You thrive in uncertainty and strive to bring order to it. You keep your eye on the ball; you build strong relationships; and you are constantly looking to improve yourself and your team.

Minimum Qualifications

MS or PhD in a quantitative modeling and data science discipline such as machine learning, computer science, statistics/biostatistics, health informatics or similar Strong background in developing deep learning, foundation, and/or generative AI models for multiple data modalities (time series, images, language, etc.) for applications in health Experience applying a scientific approach to machine learning modeling from defining hypotheses, designing experiments, testing, failure analysis, and guiding data collection in user studies Strong working knowledge of Python, Spark, or equivalent and running experiments with data at scale

Preferred Qualifications

Hybrid scientist/engineer who can do modeling, data pipelining, and/or on-device implementation Experience developing generative AI systems, such as large language models, in an applied setting, including post-training techniques like supervised fine-tuning, adapter training, and reinforcement from human feedback Excellent interpersonal skills and communication (written and verbal) Experience working with cross-functional and/or interdisciplinary teams Familiarity with privacy-preserving ML techniques is a plus