Working Student in Visual Representation of Technical Diagrams for LLMs - remote possible
Working Student in Visual Representation of Technical Diagrams for LLMs - remote possible
Employer Active
Job Alert
You will be updated with latest job alerts via email
Share
Job Alert
You will be updated with latest job alerts via email
Job Description
- During your assignment you will research optimal methods for processing and representing technical diagrams available solely as graphics for integration with Large Language Models (LLMs). You will explore the challenges and limitations of current multimodal LLMs when handling visual data and propose novel approaches for diagram comprehension.
- You will design and implement a pipeline for creating a synthetic dataset that links technical diagrams to textual descriptions in both directions (diagramtotext and texttodiagram). In addition you will investigate how variations in synthetic dataset quality and structure influence model training and performance.
- Furthermore you will conduct rigorous testing of the trained model on realworld technical diagrams from diverse domains such as engineering biology or software development. On top of that you will develop metrics to assess the models ability to interpret explain and generate meaningful outputs based on diagram inputs.
- Moreover you will perform a comparative analysis of stateoftheart multimodal models to determine their strengths and limitations in handling technical diagram as well as identify key factors (e.g. model architecture training data) that influence performance on diagramrelated tasks.
- Finally you will investigate the potential of an abstract markup syntax to serve as a universal intermediate representation for technical diagram as well as evaluate how such a syntax could improve model interpretability training efficiency and generalization across domains. You will prototype and test possible syntaxes assessing their practicality and alignment with existing diagramming standards.
Qualifications :
- Education: Master studies in Computer Science Data Science or comparable
- Experience and Knowledge: proficiency in Python ideally some prior experience in building RAG systems or chatbots
- Personality and Working Practice: a selfdriven proactive and solutionoriented individual with an independent work ethic
- Enthusiasm: strong passion for developing the best possible solutions
- Languages: fluent in English
Additional Information :
Start: according to prior agreement
Duration: 6 months 10 h/week
You want to work flexibly from your home in Germany or prefer working at the Bosch location in Abstatt For positions with the addition remote possible you can agree on the appropriate collaboration for your task together with your manager and your team within the framework of Smart Work.
Requirement for this working student position is the enrollment at university. Please attach your CV transcript of records enrollment certificate and if indicated a valid work and residence permit.
Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore we welcome all applications regardless of gender age disability religion ethnic origin or sexual identity.
Need further information about the job
Simon Klug (Functional Department)
#LIDNI
Remote Work :
No
Employment Type :
Parttime
Employment Type
Part-time
