Doctoral student in Computer Science - Secure Distributed AI
Core
Researching explicit interaction protocols and execution guards to secure multi-agent systems (robots, AI agents, humans) and ensure robust, safe, and secure interactions.
Role type
PhD researcher in Secure Distributed AI
Builds
Novel solutions for cyber resilient AI validated in sandboxed and real operational contexts
Domain
Cybersecurity and Artificial Intelligence
Deliverable
research
Required skills
Multi-agent systems, interaction protocols, cybersecurity, distributed systems, AI safety
Preferred skills
Machine learning, runtime security assurance, agentic AI
Technologies
Multi-agent frameworks, sandboxed testing environments
Responsibilities
Analyze agent interactions, generate explicit interaction protocols, develop execution guards, test and evaluate systems in realistic environments
Seniority
PhD Candidate
