Master Thesis (f/m/x) - Neuro-Symbolic AI for Resilient On-Board Decision Making

German Aerospace Center (DLR); Oberpfaffenhofen; On-site; EUR 13,000 - 18,000; Part time

Job summary

The DLR Institute of Software Technology invites a motivated master's student to join the Flight Software Department to research neuro-symbolic AI for embedded systems, contributing to safe and reliable AI on aircraft and spacecraft.

You will design a framework, prototype on the StellarApps platform, and evaluate its performance under supervision in English or German. This position offers hands-on aerospace research experience at Oberpfaffenhofen.

Qualifications

• Currently enrolled in a Master’s degree programme in Computer Science, Applied Computer Science, Electrical Engineering or a comparable subject.
• Experience in software development for embedded systems in C, C++ or Rust.
• Experience in the field of artificial intelligence and its applications.
• You can communicate in English (supervision may be conducted in English or German).

Responsibilities

• research and evaluation of state-of-the-art neuro-symbolic AI for embedded systems
• conceptualisation and design of a neuro-symbolic AI framework
• prototype implementation of the framework on the StellarApps platform
• evaluation of the neuro-symbolic AI framework

Skills

Embedded software development

AI applications

English communication

Education

Master's student in CS/EE

Tools

C/C++ toolchain

Rust

Git

Job description

The DLR Institute of Software Technology sees software as a catalyst for research and innovation. The institute's staff, currently numbering around 200, make a significant contribution to advancements in the fields of aviation, space, energy, transportation, and security through the development of state-of-the-art software solutions and innovative research. Our areas of competence include reliable and safety-critical software systems, artificial intelligence, high-performance computing and quantum computing, human-system interaction and visualisation, software and systems engineering as well as digital platforms and digital twins.

What To Expect

In the Flight Software Department, we conduct research and develop reliable and resilient (real-time) software for aircraft and spacecraft. With our expertise in this field, we currently support approximately 20 space missions with software engineering and software quality assurance.

Modern space systems are increasingly relying on sub-symbolic AI, which, however, carries risks such as a lack of traceability and unforeseen side effects. Neuro-symbolic AI has been developed to avoid misinterpretations and unreliable behaviour. This concept combines the learning capabilities of sub-symbolic methods with the reliability of symbolic, rule-based systems. The aim is to enable transparent and robust decision-making. The aim of this Master’s thesis is to develop and test a framework that makes AI applications on spacecraft safe, robust and resilient.

Your tasks

• research and evaluation of state-of-the-art neuro-symbolic AI for embedded systems
• conceptualisation and design of a neuro-symbolic AI framework
• prototype implementation of the framework on the StellarApps platform
• evaluation of the neuro-symbolic AI framework

Your profile

• currently enrolled on a Master’s degree programme in Computer Science, Applied Computer Science, Electrical Engineering or a comparable subject
• experience in software development for embedded systems in C, C++ or Rust
• experience in the field of artificial intelligence and its applications
• You are able to communicate in English (supervision may be conducted in English or German).

We look forward to getting to know you!

If you have any questions about this position (Vacancy-ID 5928) please contact:

Andreas Lund

Tel.: [phone]