Munich, Germany
Internship Explorer
Internship Explorer
We are seeking a highly motivated and skilled Research Intern to join our dynamic team, focusing on the safety of generative AI，e.g. Large Language Models (LLMs). This internship offers a unique opportunity to contribute to cutting-edge research in the field of artificial intelligence, specifically in understanding, improving, and evaluating the reliability and robustness of the latest generative AI models. Your mission * Conduct comprehensive research on generative AI safety with a focus on assessing, enhancing, and validating their reliability and robustness in various applications. * Develop and implement innovative methodologies to test LLM reliability under diverse conditions and datasets. * Collaborate closely with a multidisciplinary team of researchers, data scientists, and engineers to integrate findings into the development of more reliable LLM frameworks. * Analyze and interpret complex data sets, utilizing advanced statistical and machine learning techniques to understand model behaviors and identify potential reliability issues. * Stay abreast of the latest advancements in Safe AI for DNN, Vision Transformers (ViT), and Diffusion Transformer (DiT) etc., applying this knowledge to improve LLM reliability. * Prepare detailed reports and presentations on research findings for both technical and non-technical audiences, contributing to research papers, patents, and other publications as required.
