About the role#
Bosch Research and Technology in Pittsburgh is seeking a student intern to advance multimodal sensor foundation models for healthcare. You will work with experienced researchers to explore how models trained on diverse sensor data learn transferable representations for health monitoring. This role focuses on combining ambient and wearable sensing with advances in self-supervised learning and multimodal foundation models to support applications like physiological monitoring, activity understanding, and caregiver support.
What you'll need#
- Currently pursuing a PhD in Computer Science, Electrical Engineering, Computer Engineering, Biomedical Engineering, Data Science, or a related field.
- Strong knowledge of machine learning and deep learning principles.
- Proficiency in Python and experience with PyTorch or TensorFlow.
- Experience with time-series modeling, multimodal learning, or sensor data analysis.
- Strong problem-solving and communication skills with the ability to collaborate in a research environment.
- Interest in applying machine learning to real-world healthcare challenges.
- Desired: Research experience in foundation models, self-supervised learning, contrastive learning, masked modeling, or transfer learning.
- Desired: Experience with physiological or behavioral sensor data like ECG, PPG, IMU, radar, or acoustic signals.
- Desired: Knowledge of signal processing, multimodal representation learning, and evaluation of model generalization or uncertainty.
- Desired: Familiarity with privacy-aware methods and publications in machine learning, signal processing, or digital health venues.
What you'll do#
- Develop foundation models for multimodal sensor data including physiological signals, motion, radar, acoustics, and other health measurements.
- Investigate self-supervised learning, cross-modal alignment, and sensor fusion methods for heterogeneous and partially labeled datasets.
- Adapt and evaluate pretrained models for healthcare tasks, focusing on generalization across individuals, sensor configurations, and environments.
- Explore model robustness regarding missing modalities, noisy signals, limited annotations, and data distribution changes.
- Collaborate with the research team to prototype health-sensing solutions and assess performance, reliability, and practical limitations.
- Document and communicate findings through internal reports, presentations, and potential publications or patents.
Location & details#
- Location: Pittsburgh, Pennsylvania.
- Work Modality: On-site.
- Employment Type: Full-time intern.
- Term: Rolling.
- Compensation: Paid position.
- Note: Sponsorship for work authorization is not available.


