PhD Student - Privacy Enhancing Technologies for LLMs and AI Agents(m/w/x)

Beschreibung

You will drive innovation in AI safety by developing novel privacy protections for LLMs, moving from theoretical research to publishing and prototyping solutions for real-world deployment.

Anforderungen

• •Master’s degree in computer science, mathematics, engineering, or related field
• •Background in machine learning, deep learning, or natural language processing
• •Proficient Python programming and deep learning framework experience
• •Familiarity with large language models and agent-based systems
• •Interest in research and rigorous problem formulation
• •Knowledge of ML privacy and security techniques (plus)
• •Prior research experience or publications (advantageous)
• •Excellent written and spoken English

Aufgaben

• •Review state-of-the-art privacy research for LLMs
• •Monitor emerging attack vectors and defense mechanisms
• •Develop novel privacy-enhancing methods for AI agents
• •Address risks like data leakage and memorization
• •Implement proof-of-concept prototypes of proposed methods
• •Evaluate prototypes on public and industrial datasets
• •Publish findings in leading scientific journals
• •Present research at top-tier machine learning conferences
• •Collaborate on interdisciplinary machine learning topics
• •Coordinate with team members on agent architectures

Tools & Technologien

Benefits