Working Student in NLP

Implementation of Natural Language Processing (NLP) approaches: feature extraction (LLM-supported, embedding-based and "classical" feature engineering), style change detection algorithms (Style Change Detection), detection of AI-generated text content and attribution of which LLM generated which text, optimization of existing authorship analysis procedures (attribution and verification); Implementation and application of various machine learning methods/concepts: One/Binary-Class-Classification (LLM-based, deep learning approaches, classical approaches), ensemble methods, evaluation of ML models, development of UIs and web apps (fastHTML, Streamlit, Gradio, Angular, Svelte), participation in publicly funded and/or industry-commissioned projects

Very good academic performance with a maximum average grade of 2.2; Sound knowledge of Python and frontend development are mandatory and will be tested in the interview; Sound knowledge of machine/deep learning; Familiar with various neural network architectures (including Transformer, MLP, 1D-CNNs); Familiar with basic terms and concepts such as: classification, hyperparameter optimization, fine-tuning, model evaluation; Advantage: ability to implement methods and procedures from scientific publications independently; Advantage: knowledge and experience in cybersecurity; Willingness to take on new challenges; Strong analytical thinking

Work on-site at Fraunhofer SIT in Darmstadt (remote work not possible); Attractive remuneration: €18.06/hour for bachelor students and €18.78/hour for master students; Flexible working hours that can be easily combined with studies; Inspiring work environment with state-of-the-art infrastructure; Opportunity to gain practical experience and make valuable contacts in research; Possibility for later bachelor's and master's theses; Monthly working hours of 40 to 80 hours, by agreement