Doctoral Researcher – Multimodal AI for Digital Model Synthesis | Doktorand (w/m/d) – Multimodale KI zur Synthese digitaler Modelle

Job Summary

This Doctoral Researcher position focuses on pioneering multimodal Artificial Intelligence methods to automate the interpretation and generation of complex geometric data. The role involves analyzing and designing generative AI models, particularly utilizing Large Language Models (LLMs), to transform visual specifications into structured digital representations. Key responsibilities include developing algorithms for the semantic analysis of technical documentation and converting it into machine-readable formats, and collaborating closely with engineers and data scientists to validate AI models for industrial applications. A successful candidate will conceptualize, implement, and evaluate prototypes for synthesizing 3D digital twins from 2D representations. This is an attractive opportunity for a highly creative individual with a Master's degree in a relevant technical field, strong programming skills in Python, and foundational knowledge of Computer Vision and Generative AI, seeking to solve complex scientific challenges in a dynamic research environment.