Machine Learning Engineer - Sensing & Connectivity

The Applied Sensing & Health team has built innovative ways for users to improve

their health and fitness. When you exercise and move with your devices, it’s the

sensor fusion algorithms from the engineers and scientists on this team, that

track human motion and provide interpretable insights. Join us to work with

people who have expertise and passion to model human movement, ambient sensing,

and more to have a positive impact in users’ lives. As a member of our dynamic

group, you will have the unique and rewarding opportunity to develop state of

the art multimodal fusion of sensors, shape and contribute to the intelligence

of upcoming products that will delight and inspire millions of Apple’s customers

every single day.

DESCRIPTION

The Applied Sensing & Health team delivers Health and Fitness features for Apple

Watch, iPhones and other Apple products. We are looking for ML engineers who

care deeply about their craft to join us. The roles and responsibilities include

scoping, designing and implementing models for Health and Fitness algorithms,

validating algorithms with synthetic data flows and real datasets with

generative AI, and coordinating closely with multi-disciplinary teams across the

company. You will work with scientists, engineers, QA, and project managers

throughout the software lifecycle in successfully delivering best-in-class

secure and scalable systems. Most importantly, you will help ship features that

impact millions of users on a daily basis.

MINIMUM QUALIFICATIONS

MS 3 + years experience in quantitative data science discipline

(statistics/biostatistics, epidemiology, computer science). Strong background in

developing machine learning and/or deep learning models, preferably with time

series data. Strong proficiency in Python and ML frameworks e.g. PyTorch,

Tensorflow

PREFERRED QUALIFICATIONS

Ph.D or 5+ years experience in quantitative data science discipline

(statistics/biostatistics, epidemiology, computer science). You can form

hypotheses, and can creatively apply different statistical approaches to the

data in proving the hypotheses. You appreciate the computational and storage

complexities that come with modeling using large datasets. You leverage

distributed compute/storage models when the scale of data calls for it. You

believe that the integrity of the tooling and pipelines are critical to coming

up with high quality analyses, and are creative and disciplined about

validation. You understand the role feedback plays in your growth, and how

effective communication affords more feedback opportunities.