PhD Fellowship and Postdoc in Explainable AI, LLM Security, and Mechanistic Interpretability University of Copenhagen in Denmark

📣 A postdoctoral position is open in Mechanistic Understanding of AI Reasoning at the University of Copenhagen (Department of Computer Science, DIKU) and the Pioneer Centre for AI . The project is embedded in Isabelle Augenstein’s ERC-funded research project Explainable and Robust Automatic Fact Checking (ExplainYourself) . The role focuses on mechanistic interpretability , AI reasoning , and foundational research related to explainable AI and automatic fact checking . This is a two-year contrac...

Fully funded PhD Fellowship in Resource Efficiency for Generative AI at the University of Copenhagen , Department of Computer Science (DIKU), in the Inference & Retrieval Lab within the Machine Learning Section. The project focuses on resource efficient and sustainable Generative AI , including Large Language Models (LLMs) and AI agents . Research directions may include novel algorithms, training and learning paradigms, prompting and inference strategies, hardware-aware optimisation, and broader...

Postdoctoral Researcher position in Mechanistic Understanding of AI Reasoning at the University of Copenhagen , within the CopeNLU group and the Pioneer Centre for AI . The project focuses on how large language models acquire, integrate, and reason over evolving, pluralistic knowledge using mechanistic interpretability methods. The research may include developing novel conceptual frameworks, methods, or empirical studies. The postdoc will also contribute to teaching or supervision to a small deg...

New PhD opportunity at Aalborg University (Department of Electronic Systems, Copenhagen Campus, Denmark) in secure and privacy-preserving collaborative language models . The project, #WHISPERS , is funded by the Independent Research Fund Denmark Inge Lehmann programme and focuses on how to secure private data while using foundation models such as large language models in a distributed setting. Research topics include, but are not limited to, secure computation , distributed and decentralized lea...

The Applied Research Laboratory for Intelligence & Security (ARLIS) at the University of Maryland, College Park is hiring for a Machine Learning Application Engineer role supporting government-sponsored work in machine learning , natural language processing , computer vision , human-machine teaming , and operational analytics. This is a staff/faculty regular opportunity with multiple levels available across two tracks: Research Specialist and Research Engineer . The work focuses on building end-...