Intelligent Requirement Review Assistant using RAG in Polarion (exjobb)

The opportunity:

We are looking for a master thesis student at our R&D department, would like to join our multinational organization with lots of development opportunities. Our team is dedicated to creating a future where innovative digital technology brings cleaner energy to people around the world. If this opportunity excites you, we encourage you to apply!

In large-scale engineering environments, requirement management platforms like Polarion contain thousands of interconnected requirements, specifications, and design documents. Manual review of these requirements for completeness, consistency, and traceability is time-consuming and error prone. Retrieval-Augmented Generation (RAG) offers a novel approach by combining semantic search with generative AI to assist engineers in reviewing requirements intelligently.

How you'll make an impact:

• Develop and deploy cutting-edge transformer-based models to convert complex requirements into semantic vectors for high-precision retrieval.
• Build a robust vector search engine and integrate it with a powerful LLM to detect inconsistencies, missing dependencies, and improvement opportunities across thousands of interconnected documents.
• Evaluate the assistant's performance using real-world data and metrics like precision, recall, and user feedback-delivering insights that shape future engineering workflows.
• Deliver a working prototype that enhances review efficiency and quality, empowering engineers to make faster, more informed decisions.
• Contributes to the evolution of AI-assisted requirement management by publishing findings and recommending best practices for integrating RAG into enterprise systems.
• Living Hitachi Energy's core values of safety and integrity, taking responsibility for your actions while caring for colleagues and the business.

Your background:

• Bachelor's degree in computer science, Software Engineering, Data Science, or a related field.
• Proficiency in Python and experience with machine learning libraries (e.g., scikit-learn, TensorFlow, PyTorch).
• Familiarity with natural language processing and transformer-based models (e.g., BERT, OpenAI embeddings).
• Experience with requirement management tools (e.g., Polarion) and APIs.
• Knowledge of vector databases (e.g., FAISS, Pinecone) and semantic search techniques.
• Prior experience in AI-based document analysis or requirement engineering is advantageous.

More about us:

Are you ready for an exciting new challenge? Does the above description sound like you? Applications will be reviewed on an ongoing basis, so don't delay - apply today! Recruiting Manager: Lucas Bottura, lucas.bottura@hitachienergy.com and thesis supervisor: Hasan Basri Celebi, hasan-basri.celebi@hitachienergy.com will answer your questions about the position.

Don't hesitate - apply today and let us learn more about you and the unique contributions you can bring to our team.

Apply now

Current employees apply here

Client-provided location(s): Västerås, Sweden, Ludvika, Sweden

Job ID: Hitachi_Energy-JID3-158046

Employment Type: PART_TIME

Posted: 2025-09-30T23:35:00