Postdoctoral Researcher in Multi-Agent AI (Cybersecurity, Remote)

Job summary

A postdoctoral researcher is sought for a two-year position focused on multi-agent AI systems for cybersecurity operations, specifically within the VANTAGE project aimed at enhancing security operations through advanced AI technologies.

Qualifications

• PhD in Computer Science, Cybersecurity, Artificial Intelligence, or a related field.
• Strong background in at least two of the following areas: Large Language Models (LLMs), Generative AI, multi-agent systems, cybersecurity and vulnerability assessment, network security, incident response, AI reasoning, and prompt engineering.
• Proven publication record in reputable venues.
• Proficiency in Python and AI frameworks (e.g., PyTorch, TensorFlow, HuggingFace).
• Experience with penetration testing tools or vulnerability analysis platforms is a plus.
• Excellent written and spoken English.
• Ability to work in interdisciplinary and multicultural teams.

Responsibilities

What We Offer

• Design and implement LLM-enabled multi-agent AI systems for cybersecurity operations.
• Develop reasoning and chain-of-thought-based decision models for automated incident investigation.
• Integrate AI modules with vulnerability scanning and penetration testing tools.
• Conduct large-scale experimental validation and benchmarking.
• Contribute to system evaluation under realistic SOC/CSIRT scenarios.
• Publish high-quality research papers in leading conferences and journals.
• Contribute to project deliverables, technical reports, and dissemination activities.
• Participate in consortium meetings and technical coordination activities.
• Full-time postdoctoral position for 24 months.
• Access to high-performance computing infrastructure and advanced AI resources.
• Opportunity to collaborate with leading academic and industrial partners.
• Strong support for publication and career development.
• Work in a country known for its excellent health and education systems.