Descripción
About the position We invite applications for a PhD Research Fellow position in Knowledge-Grounded LLM Agents for Defensive Cyber Operations, available at the Digital Security Research Group within the Department of Informatics at the University of Oslo. Starting date as soon as possible and no later than 01.05.2027. The fellowship period is three years. A fourth year may be considered, which would involve 25% other career-promoting work. Other career-promoting work may consist of teaching, supervision, and/or research assistance. This depends on the applicant's qualifications and the department's current needs. No one can be appointed for more than one PhD Research Fellowship period at the University of Oslo. Project description The position will investigate knowledge-grounded and neuro-symbolic approaches to large language models and agentic AI for defensive cyber operations. The PhD project will be carried out in close collaboration with the Norwegian Defence Research Establishment (FFI), including co-supervision from FFI with potential to connect the research to relevant cybersecurity and cyber-defence challenges. The research will explore how heterogeneous cybersecurity intelligence and evidence sources, including telemetry and observations, can be transformed into structured cybersecurity knowledge, represented through semantic knowledge graphs, and combined with symbolic reasoning, modern language models, and autonomous agents to support security analysis, situational awareness, decision-making, and response. Particular emphasis will be placed on developing trustworthy, reliable, interpretable, and secure AI systems, including methods for grounding, reasoning, validation, and the control of agentic behaviour in security-critical environments. The security and robustness of LLM-based and agentic systems, including adversarial manipulation, uncertainty, provenance, and the validation of AI-generated decisions and actions, may also be explored as part of this po