Master Thesis - Västerås

Req ID:474711 

At Alstom, we understand transport networks and what moves people. From high-speed trains, metros, monorails, and trams, to turnkey systems, services, infrastructure, signalling and digital mobility, we offer our diverse customers the broadest portfolio in the industry. Every day, more than 80 000 colleagues lead the way to greener and smarter mobility worldwide, connecting cities as we reduce carbon and replace cars.

We are looking for a Master thesis student to join our team in Västerås!

Topic proposed: Developing a Searchable Document System for Alstom Product Development

Duration: 20 weeks (Master) / 10 weeks (Bachelor), on site

Background

Alstom, a leading train manufacturer, generates numerous documents during product development. These documents, encompassing hardware, software, and product-related information, are stored in various formats including text documents, pictures, and datasheet files. To enhance accessibility and productivity, we aim to set up a system that makes these documents easily searchable. In same time, AI-based solutions, such as Retrieval-Augmented Generation (RAG) combined with large language models (LLMs), have been developed to address these challenges, providing efficient and smart ways to retrieve information. An overview image can be seen below:.  

Problem description and goals

Our objective is to evaluate the implementation of a RAG solution on one or multiple projects, and then to estimate the scalability of this solution, mainly compare to a trained generative model:

1. Strategy Evaluation: State-of-the-art about the technologies to vectorize and precompute search functionalities, leveraging RAG and LLMs. Propose a strategy, based on one or multiple RAG solutions that meet the specific context of Alstom documentation.

2. Document Processing Implementation: Implementing and evaluating the most promising solutions based on relevant criteria (e.g., hardware requirements, vectorization, speed, accuracy, reliability, and prevention of fabricated information)

All about you

· Background: Software engineering, artificial intelligence/machine learning, including LLMs.

· Skills: Strong analytical abilities, systems thinking, and familiarity with hardware and mechanical/electrical engineering.

· Language: The thesis should be written in English.

Things you’ll enjoy

Join us on a life-long transformative journey – the rail industry is here to stay, so you can grow and develop new skills and experiences throughout your career. You’ll also:

• Collaborate with transverse teams and helpful colleagues
• Contribute to innovative projects
• Benefit from our investment in your development

You don’t need to be a train enthusiast to thrive with us. We guarantee that when you step onto one of our trains with your friends or family, you’ll be proud. If you’re up for the challenge, we’d love to hear from you!

Important to note

As a global business, we’re an equal-opportunity employer that celebrates diversity across the 63  countries we operate in. We’re committed to creating an inclusive workplace for everyone.