The Institute for AI Safety and Security provides research and development services in the field of AI-related methods, processes, algorithms and execution environments. The focus is on ensuring safety and security for AI-based solutions in ambitious application classes. “Safety and security by design” is a central aspect in this context, since it directly supports future requirements of safety-critical applications that are based on AI or integrate AI-based components.

Main Research Areas of the Institute for AI Safety and Security are:

• development processes and methods for safety-critical AI applications
• robust and reliable approaches to safeguard AI methods and algorithms
• safety and security in the context of AI-based applications
• management and use of sensitive data
• execution environments for AI-based applications
• innovative computation methods

The Department for Safety-Critical Data Infrastructures of the institute deals with data and information quality as well as the foundations for the development of secure, decentralized data infrastructures. One main area of the department is the development of methods and technologies with a focus on data sovereignty and semantic interoperability for critical and sensitive application scenarios.

The advertised position includes the following scientific topics:

• research and development on ontological concepts with regard to the topic of "semantic integration" of decentralized data sources
• scientific research on studies and specialist information related to procedures and challenges in the development of concepts and further developments in the field of ontologies and semantic integration - also from the "security-by-design" point of view.
• analysis and research of ontologies and their parts for a safe and robust application of AI systems of different kinds
• derivation or synthesis of "reference" concepts and their comparison with implemented or ongoing standardization activities
• analysis of possible approaches to the integration of ontologies as a basis for semantic integration in decentralized data and service ecosystems (cf. GAIA-X and IDSA)
• familiarization with the underlying subject complex of the Gaia-X Federation Services, including the subsequent application
• processing of subtasks within the framework of DLR internal and external research and development projects
• derivation of options for action for scientific and industrial applications in the context of ontologies and semantic integration
• development of a demonstrator to present the research results