Wissenschaftliche*r Mitarbeiter*in LLM-Transparenz
Core
Developing a framework to systematically evaluate the robustness of large language models (LLMs) and implementing transformation modules for linguistic, emotional, and positional context variations.
Role type
Research scientist (LLM robustness & evaluation)
Builds
Robustness evaluation framework for LLMs
Domain
Artificial Intelligence / Natural Language Processing
Deliverable
research
Required skills
Deep Learning, Transformer architectures, Large Language Models (LLMs), Python, PyTorch
Preferred skills
Academic publication experience, grant writing
Technologies
PyTorch, Python
Responsibilities
Develop a framework for systematic LLM robustness evaluation; Conceive and implement transformation modules for context variations; Conduct robustness analyses and build a structured results catalog; Write scientific publications and contribute to research proposals
