Master Thesis: Benchmarking LLM Models for Geometry Assurance Tasks

Transport is at the core of modern society. Imagine using your expertise to shape sustainable transport and infrastructure solutions for the future. If you seek to make a difference on a global scale, working with next-gen technologies and the sharpest collaborative teams, then we could be a perfect match.

Background and Motivation How do we build AI engineering agents that are fast, capable, and affordable?

Agentic AI is rapidly finding its way into mechanical design and automotive Original Equipment Manufacturers (OEMs), creating new opportunities to automate complex engineering tasks and workflows. Large Language Models (LLMs) are rapidly changing how intelligent engineering tools are built. Models are becoming more powerful, but choosing the “best” model is no longer straightforward. API and token costs can become significant when an agent performs hundreds or thousands of calls, while running models locally may reduce API dependency but introduce new challenges related to GPUs, memory, inference speed, energy consumption, and model optimization.

What will you do? In this thesis, you will explore how different LLMs can be used to build efficient and costeffective AI agents for geometry assurance tasks. You will compare models based on their task performance, reasoning quality, reliability, and cost. The study will also investigate how different software frameworks and hardware affect overall performance and efficiency. Based on your findings, you will develop a benchmarking framework and

provide recommendations for choosing the best combination of LLM, software, and hardware for future AI agents.

Who are we looking for? We are looking for a curious student who enjoys experimenting with new technologies and turning research questions into working solutions.

Candidate profile: Having 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

Experience with local LLM deployment, high performance computing, cloud platforms, is

a plus.

The thesis project is intended for 2 students. 30ECTS each.

Application: Please apply no later than 1st November, please not that this position may be filled prior to the last application date.

Location: Göteborg, Sweden.

Time Schedule: Jan 2027- Jun 2027

Contact Persons Manager: Mikael Rydh - Volvo TTI, Mail: [email protected]

Supervisor: Wenting Hu - Volvo TTI, Mail: [email protected]

Examiner: Chalmers

We value your data privacy and therefore do not accept applications via mail.

Who We Are And What We Believe In We are committed to shaping the future landscape of efficient, safe, and sustainable transport solutions. Fulfilling our mission creates countless career opportunities for talents across the group’s leading brands and entities.

Applying to this job offers you the opportunity to join Volvo Group . Every day, you will be working with some of the sharpest and most creative brains in our field to be able to leave our society in better shape for the next generation. We are passionate about what we do, and we thrive on teamwork. We are almost 100,000 people united around the world by a culture of care, inclusiveness, and empowerment.

Trucks Technology & Industrial Division hire team players who are ready to create real customer impact. Our decentralized teams work close to our customers, with speed and autonomy, to build what they truly need.

Join us to collaborate on innovative, sustainable technologies that redefine how we design, build, and deliver value. Bring your curiosity, your expertise, and your collaborative energy, and together, we’ll turn bold ideas into tangible solutions for our customers and contribute to a more sustainable tomorrow.