PhD position in machine learning, forecasting and time series analysis

Reykjavik University invites applications for a full-time, on-site PhD position in machine learning, forecasting and time series analysis. Reykjavik University, Department of Engineering. Duration: 3 years. Start date: Negotiable. Reykjavik University invites applications for a full-time, on-site PhD position. The position is funded through the LUMI AI Factory (EuroHPC) and focuses on scalable AI-for-science workflows using GPU-accelerated computing. This particular position focuses on time-series analysis and forecasting using transformer based foundation models. About the Project Time-series prediction using transformer based models is currently in a unique position of benefiting from the hindsight of billions of dollars spent in research and development in large-language models (LLMs). This second-mover advantage position creates opportunities for research and development on foundation models that can be duplicated and fine-tuned to tackle specific needs, as well as further developing promising avenues such as chain-of-thoughts and reasoning tokens, which forces the model into a reflective state transparent to the user. Interpretability emerges as a key factor when integrating the model in critical industries. The inclusion of exogenous variables, both historic and future, is also an essential ingredient to move past the rear-mirror approach of standard classical forecasting methods. The project will focus on the use of transformer based architecture, including inverted transformers, to create a practical foundation models for time series forecasting focusing on the manufacturing industry. The models will be trained on both large datasets and synthetic data, with the goal of delivering easily fine-tunable models capable of classification, forecasting, imputation, and anomaly detection. Qualifications: A Master’s degree in Engineering, Computer Science, or a related field. Strong analytical and problem-solving skills. Strong programming skills. Ability to work both independently and collaboratively. Proficiency in written and spoken English.