In Toyota Material Handling Europe, we are over 13,500 colleagues passionate about supporting companies of all sizes with todays and tomorrow’s material handling challenges. Because we know that our business and our industry are essential and sometimes even critical for you, for daily life and society at large.
In a rapidly growing high-tech industry in fast transformation, Toyota Material Handling Europe is stable, global and influential. We are committed to continuous improvement and innovation and we aim to strengthen our capabilities as a learning organisation.
Background
Data Quality is a paramount factor in many different areas, and as such, it is important to keep the quality as high as possible. Poor data quality can lead to flawed analytics, misguided decisions, and significant financial losses. In today’s data driven world, organizations rely on accurate, complete, and consistent data to power AI models, automate processes, and gain competitive insights. However, manual data quality checks are time-consuming and prone to human error. This thesis explores automated data quality testing, a scalable approach that leverages AI to ensure data integrity with minimal human intervention. By automating these checks, businesses can improve efficiency, reduce risk, and unlock the full potential of their data assets.
At Toyota Material Handling Europe, we work with big data at scale across multiple domains, including Business Intelligence (BI). Ensuring data quality in such environments is critical because even minor inconsistencies can cascade into major operational and strategic errors.
Problem Statement
Despite the growing importance of data quality, most organizations still depend on manual or rule-based processes that cannot keep pace with the volume and complexity of modern datasets. These traditional methods often fail when it comes to more complex issues, such as contextual anomalies, semantic inconsistencies, or patterns indicating systematic data transformation errors, leading to unreliable analytics and operational inefficiencies. In large-scale environments like Toyota Material Handling Europe, where data powers BI dashboards and decision-making, the challenge becomes even more pronounced. There is a growing need to explore how AI can support the identification of such subtle and hard-to-detect data quality problems. By leveraging AI to understand data patterns and flag anomalies, we aim to move towards more intelligent and proactive data quality assurance.
Thesis Objectives
The thesis will focus on:
- Investigate how AI techniques can be applied to detect complex data quality issues that are not easily captured by traditional validation methods.
- Identify and implement key data quality dimensions (e.g., accuracy, completeness, consistency, freshness, anomaly detection) in an automated testing pipeline.
- Evaluate the performance and scalability of the proposed solution on production ready datasets.
- Provide insights and recommendations on how AI can be incorporated into a long-term strategy for proactive data quality assurance.
Your Contribution
As a thesis student, you will:
- Will work with technology such as Snowflake, Python, AI & ML, Azure DevOps and Pipelines.
- Have access to an AI playground environment where you can utilize LLMs and ML tools
- Explore how AI can be used to detect complex and subtle data quality issues beyond traditional rule-based checks.
- Investigate what metrics are important to ensure data quality
- Investigate how to automate and flag for erroneous data points and how to amend them
- Create end-to-end pipelines to run the tests and notify about relevant failures
- Benchmark proposed solution against traditional methods
- Provide guidelines and recommendations to adopt for future reference
- A report describing the proposed approach, findings and recommendations
Your Profile
We are looking for:
- 1–2 Master’s students in relevant programs such as Computer Science, Data Science, AI & ML, or Information Security.
- Students who are passionate about data and eager to improve data quality across diverse systems.
- Individuals who want to innovate using the latest technologies and drive meaningful change.
- Curious and proactive learners who enjoy problem-solving, automation, and working with cutting-edge tools.
Your Application
Send your application as soon as possible and no later than November 27th 2025. We review applications continuously, so don’t wait to apply. We’re not looking for perfect. We’re looking for curious, courageous, creative minds who want to MOVE the World with us.
Applications should include:
- CV
- A short personal letter
- Transcript of records
For more information about the thesis please contact Head of data and advanced Analytics Rikard Larsson; Rikard.Larsson@toyota-industries.eu or Data scientist Ahmad Al- Mashahedi; Ahmad.Al-Mashahedi@toyota-industries.eu
For information about your application or the recruitment process, please contact Recruitment Specialist Victoria Östryd Söderlind; victoria.ostrydsoderlind@toyota-industries.eu
#LI-DNI
