Start date: February 2025
Assignment Duration: 6 to 9 months
Location: Veghel
Educational Level: Master
Desired Study: Data Science or related studies
Language: Dutch / English
Assignment
We are looking for an ambitious student to take on a challenging graduation assignment focused on enhancing our predictive maintenance services. The core objective of this assignment is to evaluate our predictive maintenance services automatically. This involves analyzing field and ticket data, which are crucial for accurate evaluation of our models.
However, one of the main challenges is that ticket data is often spread across various platforms and formats, making it unstructured and difficult to analyze. Your task will be to develop a method or tool to consolidate and structure this data, enabling more effective and automated evaluations of our predictive maintenance services.
Given the complexity of handling unstructured ticket data, Large Language Models (LLMs) offer a promising solution to streamline this process. By efficiently parsing and interpreting unstructured data, LLMs can significantly enhance our predictive maintenance services. Their advanced capabilities allow for the extraction of meaningful patterns and insights from disparate data sources, which in turn improves predictive accuracy and operational efficiency.
Department
The intern will work in the Digital Service Platform department, responsible for driving Vanderlande digital transformation through the creation of Digital Services. He or she will be working in the Predictive Maintenance team, a multidisciplinary, multicultural and distributed team focused on converting data into insights to drive and optimize Maintenance. The team has data science, data engineer, software development and frontend development capabilities.
The student will have ample support and access to the existing knowledge within the team. If the internship is successful, their work will be used by the team to improve and enlarge the existing product.
Your responsibilities
- Collect and consolidate unstructured ticket data from various platforms and formats
- Gain a comprehensive understanding of the predictive maintenance domain and Vanderlande's specific needs
- Develop a method or tool to structure and analyze the collected data for accurate model evaluation
- Investigate the feasibility of automatic label generation for ticket data using Large Language Models (LLMs)
- Collaborate with the Predictive Maintenance team to integrate the developed solutions into existing workflows
Your profile
- Data science and ML knowledge
- LLM knowledge
- Python knowledge
- (Preferred) Familiarity with Azure and Databricks
- Mandatory enrolment in a Dutch Education System and resident of The Netherlands*
Contact
Do you recognize yourself in this challenging profile? And are you looking for an internship/graduation assignment in our organization?
Please fill out the application form and upload your resume and cover letter. For more information, contact us by e-mail: internship@vanderlande.com