PhD Research Summer Intern AI/ML & Digital Health

PhD-level AI/ML research internship focused on developing foundation models for multimodal wearable sensor data in digital health. The role emphasizes self-supervised and multimodal representation learning across health tasks.

• Design and implement selfsupervised learning frameworks for wearable timeseries data
• Train foundation models on large-scale unlabeled multimodal sensor datasets
• Develop architectures using transformers, contrastive learning, masked modelling, and crossmodal attention
• Integrate heterogeneous sensors using multimodal fusion strategies
• Evaluate learned representations on downstream health tasks (HAR, sleep, stress, gait, health outcomes)

Scope includes building AI/ML models for timeseries wearable data, using transformers and self-supervised learning, with emphasis on multimodal fusion across accelerometer, PPG, and ECG signals; aims to publish reproducible research and produce well-documented code.

The ideal candidate is a PhD candidate in ML/CS with strong Python and DL experience (PyTorch or TensorFlow), who has worked with self-supervised and multimodal learning on wearable sensor data for digital health applications.