Postdoctoral Fellowship (05) at Linkoping University, Sweden

This position focuses on the development of theoretically grounded and practically scalable decentralized learning algorithms under realistic system constraints, including communication limitations, adversarial conditions, continual and adaptive learning in dynamic environments.

The research will combine tools from distributed optimization, stochastic approximation, information theory, and learning theory to design efficient and robust decentralized AI systems.

The multi-disciplinary centre for cyber resilient AI, RESIST, is a national effort funded by the Swedish Strategic Research Foundation (SSF) to bring together leading researchers in AI and cybersecurity to develop novel solutions to cyber-resilient AI for the benefit of Swedish industry and society. The vision is to make Sweden a role model in secure trustworthy AI by pioneering cyber resilience across the AI lifecycle. The research program focuses on four key themes: Trustworthy and Verifiable AI, Runtime Security Assurance, Robust and Secure AI-Supported Development, and Resilient Distributed and Agentic. RESIST will drive world-class research in the intersection between AI and cybersecurity through a strong, stimulating and well connected international research environment. Research outcomes will be validated in real world scenarios with industry and public-sector partners. RESIST will also serve as a national hub for cyber resilient AI, promoting education, knowledge sharing, and policy development.

For this position, we are looking for a postdoc candidate who will advance the research frontier in Trustworthy and Verifiable AI within this collaborative national project.

AIR² is a five-year multidisciplinary national project financed by the Wallenberg AI, Autonomous systems, and Software Program (WASP) whereby you will have the opportunity of collaboration with top researchers within cybersecurity, networking, AI planning, and cloud computing, both within our department and two other universities in Sweden (KTH and Umeå University). The project is coordinated by Professor Simin Nadjm-Tehrani within the Cybersecurity division at Linköping University, and aims to understand the cybersecurity challenges in software-intensive and high-performance communication networks using AI-powered methods.

We will advance the research front in defending future generation networks by:

• prevention of cyberthreats through anticipating and mitigating them,
• accurate detection of ongoing attacks with well-understood AI methods used for system and network monitoring,
• (partially) autonomous and explainable reaction to attacks in presence of resource trade-offs and complex potential changes over time (concept drift).

The project is financed by a NEST grant within WASP. In this project we are looking for an excellent candidate who has a strong background in the following areas as evidenced by earlier research publications; Creation of virtualised container-based testbeds for experimental research on network security, integration of industrial use cases and digital twins, AI-based domain-specific emulations for new generation networks, attack generation and detection in virtualised 5G networks.

Your role will be as a researcher in a two-year project carried out in close collaboration with our industry partner. The goal is to develop methods for an ML-based decision support system for monitoring and fault diagnosis of gas turbines. The project focuses on developing an integrated approach that combines machine learning techniques with physics-based models to estimate the health of various system components. The aim is that fault diagnosis performance should improve over time as more data becomes available. The diagnostic conclusions will be presented to an operator using a combination of AI-based fault isolation algorithms and data-driven classifiers.

As postdoc, you will principally carry out research. You are expected to actively publish and present results in scientific journals and conferences. A certain amount of teaching may be part of your duties, up to a maximum of 20% of working hours.