R&D PhD Summer Intern: Data Science and Machine Learning

Procter & Gamble

3d•Onsite

About The Position

This internship is specifically designed for individuals working towards a PhD who are developing proficiency in their field. As an intern or co-op in management, you will have the opportunity to learn from experienced professionals in a supportive environment. This is a 12-week paid internship, designed to provide you with a solid foundation for future career growth. The internship will take place from May (potentially early June) to August of 2027. Join us at P&G, where your contributions will play a vital role in shaping the future of consumer products! P&G has an opportunity for a PhD intern to work in our on our corporate function R&D team using Machine Learning for Wearable Sensing & Human Motion. Reconstructing full-body human motion from a handful of noisy, drifting wearable sensors is a challenging machine learning problem, drawing on time-series modeling, multi-modal sensor fusion, human pose estimation, and biomechanics. As a PhD Intern on the CF R&D Data Science and AI team at P&G, you will work on this problem directly, and progress on it to enable new ways of understanding how people move and interact with products outside the lab. Our research sits close to the product: the models we build inform design, ergonomics, fit, comfort, and the everyday experience of using our brands. Wearable sensing lets us observe movement and product interaction in real-world settings that lab-based methods cannot reach, and it lets us ask questions such as: How much physical effort does a task actually require? How does a product move with the body? Where does the experience break down? What should privacy-preserving, in-home consumer research look like going forward? In this role, you will extend what wearable AI can do and turn those results into tools and findings that shape design decisions. You will work with teams across R&D, Brand, and Product Development to take your models from research prototype to production. Success depends on technical depth in deep learning and sensor data, combined with the curiosity, communication, and collaboration needed to work effectively with partners across functions and levels.

Requirements

Working towards a PhD in Computer Science, Electrical Engineering, Biomedical Engineering, Robotics, Applied Mathematics / Statistics / Physics (with relevant ML and sensor-data experience), or a related fields with a focus on machine learning, wearable sensing, or human motion analysis.
Research experience in one or more of the following: machine learning for time-series data, Human Activity Recognition, wearable sensing, human pose estimation, or multi-modal sensor fusion.
Strong Python programming skills and hands-on experience with PyTorch or TensorFlow.
Available to work a 12-week internship from May/early June to August in the summer of 2027. This is an in-person internship; candidate is expected to work from our Mason Business Center five days a week.

Nice To Haves

Track record of research publications in venues such as NeurIPS, CVPR, SIGGRAPH, CHI, UbiComp/IMWUT, AAAI, or similar.
Hands-on experience with IMU, EMG, or other wearable sensors.
Familiarity with biomechanics, inverse kinematics, or human body models (e.g., SMPL).
Experience deploying ML models to production or building research tools/APIs.

Responsibilities

Review the state of the art in full-body motion reconstruction from wearable sensors to inform modeling and sensor design choices for the project.
Determine optimal sensor configurations — type, number, and placement — for a range of motion reconstruction tasks.
Design, build, and refine deep learning models that convert IMU and EMG signals into accurate full-body motion.
Evaluate models rigorously on public and internal datasets and critically analyze assumptions, failure modes, and limitations.
Deliver a production-ready application that lets internal researchers upload recordings, run inference, and visualize results.