Wissenschaftliche/r Mitarbeiter/in im Bereich AI Security und Explainable AI
Core
Research and development of AI-based methods for detecting synthetic media, deepfakes, and multimodal manipulations, alongside explainable AI (XAI) procedures for security systems.
Role type
Research Scientist (AI Security & Explainable AI)
Builds
Multimodal machine learning and deep learning procedures for audio, image, video, and text data; realistic benchmarks and attack scenarios including Blue- and Red-Teaming.
Domain
Academic Research, AI Security, Explainable AI, Multimodal Learning
Deliverable
production ML models
Required skills
Machine Learning, Deep Learning, Python, PyTorch, TensorFlow, Computer Vision, Audio/Speech Processing, Natural Language Processing, Foundation Models, Agent-based AI
Preferred skills
AI Security, Adversarial Machine Learning, Deepfake Detection, XAI, Scientific Publishing
Technologies
Python, PyTorch, TensorFlow, LLMs
Responsibilities
Develop and evaluate AI-based procedures for detecting synthetic media and deepfakes; Research multimodal ML and DL procedures for cross-modal consistency checks; Investigate AI-based attack vectors and security measures; Develop and evaluate XAI procedures for multimodal security systems; Develop LLM-based explanation and narration approaches.
Seniority
Junior/Mid-level Researcher (Wissenschaftlicher Mitarbeiter)
