Computer scientist, mathematician, physicist or engineer or similar (f/m/x)

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 Algorithms & Hybrid Solutions of the DLR Institute for AI Safety & Security works, among other things, on research and development of methods and algorithms for the comprehensive verifiability of secure AI in highly critical application areas. In addition to the operational and attack security of such AI systems, the focus is on scientific and technical progress. This includes to take social challenges and the dangers of artificial intelligence into account. Specifically, we are systematically developing artificial intelligence methods and technologies in order to either make them accessible for security-related detection methods or to synthesize them in a verifiable manner. In other words, the aim is to formally prove the correctness of AI algorithms and the predictability and explainability of their components

A key aspect is the analysis and evaluation of interpretability and explainability for various AI methods.

With your work, you will make an important contribution to the responsible introduction of AI-based solutions in ambitious application classes. In particular you will work on

• Development and improvement of methods in the area of inverse reinforcement learning
• Development of safe and robust AI algorithms by analyzing the formal mathematical conditions
• Creation and development of concepts for the implementation of reinforcement learning algorithms in safety-critical application scenarios

DLR - Helmholtz / Deutsches Zentrum für Luft- und Raumfahrt

Ads