Alexandre Graell i Amat

Join our research team at Linköping University as a PhD student in the exciting field of AI Security, focusing on 'Memory Poisoning in LLM Agents: Foundations, Attacks, and Defenses'. This position is part of a collaborative effort with Chalmers University of Technology and Recorded Future, addressing critical security risks in AI systems. The successful candidate will engage in cutting-edge research, contributing to the understanding and mitigation of memory poisoning attacks in large language model agents. This role requires a Master's degree in Computer Science, Electrical Engineering, or Applied Mathematics, along with strong programming and mathematical skills. Linköping University is recognized for its excellence in AI research, providing a dynamic environment for doctoral studies. The position is fully funded, with a competitive salary and benefits. Applications are due by January 12, 2026. We encourage candidates from diverse backgrounds to apply.

Linköping University invites applications for a PhD position in communication systems, focusing on the cutting-edge area of AI security. The research topic is 'Memory Poisoning in LLM Agents: Foundations, Attacks, and Defenses.' Large language model (LLM) agents are revolutionizing artificial intelligence by integrating LLMs with external tools and memory components, enabling complex reasoning and decision-making. These agents are increasingly used in critical domains such as healthcare, finance, cybersecurity, and autonomous vehicles, where they interact with external knowledge sources and retain memory across sessions. While LLM agents offer transformative benefits, they also face new and poorly understood security risks. Memory poisoning attacks, which exploit the agent’s ability to store and adapt knowledge, pose severe threats to reliability and security, potentially leading to biased decisions, manipulation, breaches, and system failures. The project aims to develop a theoretical foundation for understanding and mitigating these attacks, contributing to the forefront of AI security research. The position is funded by the Swedish Research Council (VR) and is based in the Division for Communication Systems (KS), Department of Electrical Engineering (ISY), Linköping University. The division conducts research and education in communications engineering, statistical signal processing, network science, and decentralized machine learning. The research team includes Asst. Prof. Khac-Hoang Ngo (Linköping University), Prof. Alexandre Graell i Amat (Chalmers University of Technology), and Dr. Johan Östman (Recorded Future), with opportunities for research visits to Chalmers and Recorded Future. The team currently consists of 5 PhD students and 2 postdocs. Linköping University is recognized as a leader in AI research, ranked 43rd globally and 12th in Europe, and has been awarded 'Student City of the Year' in Sweden three times. The PhD position is full-time for four years, with possible extensions based on teaching and departmental duties. Salary is determined by a locally negotiated progression, and employment benefits are provided. Applicants must have a Master’s degree in Computer Science, Electrical Engineering, or Applied Mathematics (minimum 240 credits, with at least 60 in advanced courses), or equivalent knowledge. Strong mathematical maturity, programming skills, and excellent English communication are required. Candidates should be independent, goal-oriented, and effective collaborators. The degree requirement must be met by the time the employment contract is signed. The starting date is by agreement, but no later than January 1, 2027. To apply, submit your application via the official job page by April 20, 2026. Late applications will not be considered. For questions, contact the department or request to connect with current PhD students. Linköping University values diversity and equal opportunities, and encourages applicants from varied backgrounds.

Linköping University is advertising a PhD position in AI Security focused on the information-theoretic foundations of memory poisoning . The project studies how malicious information injected into an AI agent’s memory can affect reasoning and decision-making, with an emphasis on rigorous theory as well as proof-of-concept attacks, defenses, and experiments with LLM-based agents . The position is based in the Division for Communication Systems at the Department of Electrical Engineering , Linköping University. The research team spans Linköping University, Chalmers University of Technology, and Recorded Future, and includes work in AI privacy and security, communication theory, statistical learning, and decentralized machine learning. Research keywords: AI security, information theory, memory poisoning, LLM agents, privacy, statistical learning, communication theory, signal processing, optimization, applied probability and statistics, cybersecurity, distributed systems. Eligibility: Applicants should have a Master’s degree in Computer Science, Electrical Engineering, or Applied Mathematics (or equivalent), with at least 240 credits and at least 60 advanced credits in the relevant subjects. Strong mathematical maturity, programming skills, and excellent English communication skills are required. Prior experience in AI security, privacy, or LLMs is helpful but not mandatory. Funding: The position is funded by the Swedish Research Council (VR). The employment is normally four years full-time equivalent, with possible extension up to five years depending on teaching and departmental duties. The starting salary is around 36,400 SEK/month, with employee benefits including a pension. Application deadline: 2026-06-22. Apply through the Linköping University vacancy page.