Internship - LLM-Based Information Extraction

About the role

D ONE helps companies turn their data into value, and offers a fixed-term internship (typically 3 months, 80-100%) in Zurich for students at Bachelor, Master or PhD level. You will work independently on a topic in automated understanding of business documents, turning raw, messy documents into structured, verifiable information.

Key responsibilities

• Review current approaches to information extraction from unstructured and semi-structured documents.
• Design and implement extraction pipelines in clean, modular, well-tested Python.
• Build annotated data sets and measure extraction quality rigorously.
• Handle real-world document variety: layouts, languages, scan quality and edge cases.
• Document your work and present it to both technical and non-technical audiences.

Required profile

• Current enrolment in a Bachelor's, Master's or PhD programme in Computer Science, Data Science, Computational Linguistics, Engineering, Mathematics or a comparable field.
• Interest in at least one industry domain and curiosity about how data creates value in it.
• Pragmatic, results-oriented attitude and excellent English communication; German is a strong plus.
• Experience with large data sets and databases; preferred: NLP foundations, LLM prompting and schema enforcement, document parsing and OCR tools, annotation and extraction metrics, data protection awareness, and software engineering discipline.

Required skills

• Python, SQL, Git, Spark and cloud platforms
• Naming entities, relation extraction, text classification, and extraction metrics (precision, recall, F1)
• Preferred: Pydantic, Instructor, Outlines, JSON Schema, docling, unstructured, PyMuPDF, Tesseract, Azure Document Intelligence

What we offer

• A low-noise environment and an international team.
• Mentoring by senior consultants and access to the D ONE Academy.
• A clearly scoped topic you can shape, frequent offsite events and a realistic path to becoming a consultant.