Machine Learning Engineer

Apple’s Health Sensing team is seeking a versatile Machine Learning Engineer to develop next-generation health algorithms that deliver meaningful insights to users by combining classical ML, signal processing, and emerging generative AI techniques. Our team has delivered impactful features including heart rate notifications, ECG, blood oxygen, sleep apnea notifications, and overnight vitals to millions of Apple Watch users.

Description

This role is ideal for an engineer who enjoys moving quickly from idea to prototype to product, creatively overcoming data limitations, and applying new tools to multi-modal sensor fusion problems in health and wellness. You will work across the full algorithm lifecycle including data strategy, modeling, evaluation, optimization, and deployment.

Minimum Qualifications

Bachelors degree in Computer Science, Electrical Engineering, Biomedical Engineering, Statistics, Applied Mathematics, or related field, or equivalent industry experience. Strong foundation in machine learning, statistics, signal processing, or applied mathematics for real-world sensing problems Experience applying modern AI techniques, including generative AI and agentic AI, to accelerate algorithm development, data generation, and performance evaluation Proficiency in Python for algorithm development and optimization Demonstrated ability to rapidly prototype, evaluate multiple approaches, and iterate based on experimental results Experience owning algorithm development from early exploration through validation and integration

Preferred Qualifications

Experience developing algorithms for physiological sensing using multi-modal data Familiarity with on-device ML frameworks or resource-constrained optimization Experience working with incomplete, noisy, or limited datasets Background in experimental design and statistical validation Experience with distributed or cloud-based ML workflows Experience accelerating development through simulation, synthetic data, or creative data augmentation approaches Self-driven, curious engineer comfortable taking ambiguous sensing problems from concept to working solutions