Master Thesis Large Language Model
Eskilstuna, SE, 405 08
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.
Master Thesis
Leveraging Agentic AI and Interactive Dashboards for Autonomous Customer data Analysis and Management.
Thesis Proposal
This master thesis is suitable for one student who is completing their studies in computer science or electrical engineering. Proficiency in spoken and written English is required. The thesis will be led by Volvo Construction Equipment, Eskilstuna, Sweden. Desired start date is January 2026.
Background
Volvo Construction Equipment (VCE) is one of the world's largest manufacturers of construction equipment. With enhancing the artificial intelligent area and learning-based approaches, there is a big trend for using Large Language Models [1] for analyzing documents. To maintain a leading position, it is essential for Volvo CE to develop innovative and cost-efficient solutions for delivering AI models that learn from data and answer related questions.
Project Summary
The advent of Large Language Models (LLMs) has revolutionized natural language processing, offering unprecedented capabilities in understanding and generating human language. This thesis aims to explore the application of LLMs in document analysis, focusing on extracting, classifying, and summarizing information from diverse documents including customer claims, machine data, and log reports. A key aspect of this research is the integration of agentic AI—autonomous, goal-driven AI agents capable of interacting with data, making decisions, and performing complex tasks independently. By leveraging the contextual understanding of LLMs and agentic AI, the project will develop an intelligent system that can autonomously process and analyze large volumes of unstructured data.
Furthermore, the thesis will involve designing and implementing a user-friendly dashboard that visualizes document analysis results, enabling stakeholders to easily interpret insights, track document statuses, and manage information workflows. This dashboard will serve as an interactive interface for monitoring AI-driven analysis, facilitating decision-making and collaboration across teams.
The research will address challenges related to unstructured data handling, model scalability, and real-time processing, proposing methodologies to enhance the accuracy, efficiency, and usability of automated document analysis systems. The outcome will demonstrate how agentic AI combined with advanced visualization tools can significantly improve document management and information retrieval processes across various industries, including manufacturing, engineering, and research.
The main activities are:
- Literature Review: Conduct an in-depth review of existing methods in document analysis, focusing on LLM-based approaches, agentic AI, and visualization dashboards.
- Data Collection and Preprocessing: Collect a diverse dataset of documents and preprocess them for input into LLM-based models, ensuring coverage of multiple formats and content types.
- Agentic AI Development: Design and implement autonomous AI agents capable of interacting with documents, making decisions, and executing analysis workflows.
- Dashboard Design and Implementation: Develop an interactive dashboard that visualizes analysis results, tracks document statuses, and allows user interaction for document management.
- Integration and Optimization: Integrate the agentic AI and dashboard into a cohesive framework, optimizing for speed, accuracy, and scalability across different domains.
A comprehensive report detailing the methodology, results, and insights will be prepared and presented to staff at Volvo CE. The thesis work will be conducted at Volvo CE facilities in Eskilstuna, providing practical insights and industry relevance.
Contacts
The Volvo supervisor for this thesis project is:
Mohammad Loni
AM System Enablers, Volvo Construction Equipment, Eskilstuna, Sweden
Email: mohammad.loni@volvo.com
References
[1] Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., ... & Wen, J. R. (2023). A survey of large language models. arXiv preprint arXiv:2303.18223.
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.
Part of Volvo Group, Volvo Construction Equipment is a global company driven by our purpose to build the world we want to live in. Together we develop and deliver solutions for a cleaner, smarter, and more connected world. By unleashing everyone’s full potential, we build a more sustainable future for all our stakeholders. Come join our team and help us build a better tomorrow.