Assignment type: Graduation/Internship
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 seeking a motivated student to join our Predictive Maintenance team within the Digital Service Platform department. The primary objective of this assignment is to make the anomaly detection models used by the team more explainable and transparent. The current time series models employed for predictive maintenance need thorough evaluation and improvement to enhance their clarity and interpretability. This is a crucial step in ensuring that maintenance decisions are of good quality and that we can understand the sensitivity of our models.
As the number of models we manage continues to grow significantly, the need for explainable AI becomes even more critical. Explainability allows us to trust and comprehend the decisions made by these models, ensuring that they are reliable and accountable. In a rapidly expanding environment, clear understanding and transparency in AI models are essential for making the right decisions based on model outputs.
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
-
The student will be introduced to the predictive maintenance services the team develops and the stakeholders and experts
- Learn and understand the current anomaly detection models used by the Predictive Maintenance team
- Investigate potential frameworks and libraries for enhancing the explanation of these models
- Choose and implement appropriate measures and methods for improving model transparency and interpretability
- Apply the chosen frameworks and measures to the existing models.
- Conclude with documented recommendations
Your profile
- Data science and ML 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