Master Thesis: Benchmarking LLM Models for Geometry Assurance Tasks
Teknik, data och digitalt · Mjukvaru- och webbutveckling · Mjukvaruutveckling · Artificiell intelligens
I korthet
This Master's thesis project involves benchmarking Large Language Models (LLMs) for geometry assurance tasks within AI engineering agents. You will compare different models on performance, cost, and reliability, developing a framework for selecting optimal LLM, software, and hardware combinations.
Ansvarsområden
- Explore how different LLMs can be used to build efficient and cost-effective AI agents for geometry assurance tasks.
- Compare models based on their task performance, reasoning quality, reliability, and cost.
- Investigate how different software frameworks and hardware affect overall performance and efficiency.
- Develop a benchmarking framework.
- Provide recommendations for choosing the best combination of LLM, software, and hardware for future AI agents.
Krav
- Two or more core skills: Good Python programming skills
- Basic understanding of LLMs and Agentic AI
- Basic understanding of mechanical engineering and geometry assurance
- An experimental and analytical mindset
- The thesis project is intended for 2 students, 30 ECTS each.
Önskade kvalifikationer
- Experience with local LLM deployment is a plus.
- Experience with high performance computing is a plus.
- Experience with cloud platforms is a plus.
Förmåner
- Opportunity to shape sustainable transport and infrastructure solutions for the future.
- Work with next-gen technologies and collaborative teams.
- Gain experience in agentic AI, LLMs, and mechanical design.
- Work on a 30 ECTS thesis project.
#AI#LLM#Geometry#Benchmarking#Thesis#Student