Doctoral student in machine learning
Core
Investigate combining diffusion-based anomaly-detection methods with time-series foundation models for robust detection across heterogeneous and evolving data.
Role type
PhD researcher (machine learning)
Builds
Theoretically grounded diffusion-based methods for anomaly detection and foundation-model-based applications on heterogeneous vehicle data.
Domain
Machine learning, time-series analysis, anomaly detection, smart cities/health innovation
Deliverable
production ML models
Required skills
machine learning, artificial intelligence, data mining, signal processing, programming, analytical problem solving
Preferred skills
research in diffusion-based methods, time-series foundation models
Technologies
diffusion models, time-series foundation models, heterogeneous fleet data
Responsibilities
Research on diffusion-based anomaly detection within the time-series foundation-model framework; Publish research findings in peer-reviewed scientific venues; Complete relevant doctoral coursework; Teaching and supervision duties (up to 20%).
Seniority
PhD student (early-career researcher)
