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 The Intelligent and Distributed Systems department researches methods to make complex technical processes and systems – from software development to automated workflows and AI-assisted analysis – traceable, automatable, and interactively experimentally accessible. The Sustainable Software Engineering Group investigates how scientists and engineers develop software - and how they can be supported efficiently and effectively in doing so. In this context, an AI-supported assistance system is to be prototypically developed and evaluated as part of a thesis. The aim is to explore and test recent approaches for this task in practice, such as Large Language Models (LLMs), agent-based systems, and retrieval-augmented generation (RAG). ## Your tasks - selection and integration of suitable open source LLM models - use of Ollama (or similar tools) as an interface to local open-source LLMs - integration of dynamic knowledge sources (e.g. DLR Software Engineering Guidelines or GitLab repositories) - development of a simple agent workflow with e.g. Langchain, CrewAI or LlamaIndex - design and execution of tests ## Your profile - Student of computer science (e.g. with a focus on software engineering or artificial intelligence), data science or similar. - good knowledge of Python - practical experience in software development - basic understanding of concepts such as LLMs or API-based integration - willingness to systematically familiarize yourself with new technologies We look forward to getting to know you! If you have any questions about this position (Vacancy-ID 2491) please contact: Norman Müller Tel.: +49 2203 601 1221 Start of internal publication: Internal job advertisement deadline: