Working Student in the Field of NLP

Implementation of Natural Language Processing (NLP) approaches, including: Feature extraction (LLM-supported, embedding-based as well as "classical" feature engineering) Style change detection algorithms Detection of AI-generated text content and attribution of which LLM generated which text Optimization of existing authorship analysis methods (attribution and verification) Feature extraction (LLM-supported, embedding-based as well as "classical" feature engineering) Style change detection algorithms Detection of AI-generated text content and attribution of which LLM generated which text Optimization of existing authorship analysis methods (attribution and verification) Implementation and application of various machine learning methods/concepts, such as: One/Binary-Class Classification: LLM-based (e.g., zero/few shot learning, fine-tuning of foundation models), deep learning approaches (CNNs, transformers, Siamese NNs), classical approaches (SVM, random forest, isolation forest, kNN, etc.) Ensemble methods (stacking, voting, weighting, calibration) Evaluation of ML models based on standardized metrics (ROC, AUC, confusion matrices, etc.) Development of UIs and web apps (fastHTML, Streamlit, Gradio, Angular, Svelte) Collaboration in publicly funded and/or directly industry-partner commissioned projects One/Binary-Class Classification: LLM-based (e.g., zero/few shot learning, fine-tuning of foundation models), deep learning approaches (CNNs, transformers, Siamese NNs), classical approaches (SVM, random forest, isolation forest, kNN, etc.) Ensemble methods (stacking, voting, weighting, calibration) Evaluation of ML models based on standardized metrics (ROC, AUC, confusion matrices, etc.) Development of UIs and web apps (fastHTML, Streamlit, Gradio, Angular, Svelte) Collaboration in publicly funded and/or directly industry-partner commissioned projects

Outstanding academic record with a maximum average grade of 2.2. Profound knowledge in Machine/Deep Learning Profound knowledge of Python is mandatory and will be tested in the interview Familiar with various architectures of Neural Networks (including Transformer, MLP, 1D-CNNs) Familiar with basic terms and concepts such as: classification, hyperparameter optimization, fine-tuning, model evaluation Advantageous: ability to independently implement methods and procedures from scientific publications Advantageous: knowledge and experience in the field of cybersecurity Willingness to face new challenges Strong analytical thinking

Attractive hourly rate: €18.06/hour for Bachelor’s students and €18.78/hour for Master’s students Flexible working hours that can be easily combined with your studies An inspiring work environment with state-of-the-art infrastructure The opportunity to gain practical experience and make valuable contacts in research Possibility for later bachelor's and master's thesis The monthly working hours are 40 to 80 hours, depending on agreement