LLM-Based Information Extraction (Zurich, Switzerland)

Fixed-term contract (typically 3 months) · 80–100% · Zürich · Students (Bachelor, Master or PhD level)

«Making sense of data is the winning competence in all industries.»

We build D ONE with the belief that every company will be a data company. Since our beginnings, we help our clients to make sense of their data and generate value.

In this internship you will work independently on a topic in the area of automated understanding of business documents. You will move from raw, messy documents to structured, verifiable information, and make the approach hold up across domains.

• Reviewing current approaches to information extraction from unstructured and semi-structured documents.
• Designing and implementing extraction pipelines in clean, modular, well-tested Python.
• Building annotated data sets and measuring extraction quality rigorously.
• Handling real-world document variety: layouts, languages, scan quality and edge cases.
• Documenting your work and presenting it to a technical and a non-technical audience.

• 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.
• Down-to-earth and pragmatic results-oriented attitude.
• Experience in working with large data sets and databases.
• Knowledge in relevant technologies and programming languages (e.g. Python, SQL, Git, Spark, cloud platforms).
• Excellent communication skills in English; German is a strong plus.
• Solid NLP foundations, in particular named entity recognition, relation extraction and text classification.
• Working understanding of large language models and of prompting, structured output and function calling.
• Experience enforcing schemas on model output (e.g. Pydantic, Instructor, Outlines, JSON Schema, constrained decoding).
• Familiarity with document parsing and OCR tooling (e.g. docling, unstructured, PyMuPDF, Tesseract, Azure Document Intelligence) and with layout-aware models.
• Practical skills in annotation: guideline design, gold-standard creation and inter-annotator agreement.
• Command of extraction metrics: entity-level precision, recall and F1, span matching, and error analysis.
• Comfort working with German and English documents; further languages are welcome.
• Awareness of data protection and PII handling, including anonymisation and pseudonymisation techniques.
• Software engineering discipline: reusable Python packaging, configuration, automated tests and CI.
• Strive to understand your clients' needs.
• Deliver outstanding results with high business value in a comprehensible form.
• Have the intellectual agility required to get the job done in an easy-to-do-business-with way.
• Value clever and creative team play.
• Work independently and structure your own progress, while knowing when to pull in a senior colleague.

Are you interested in joining a great team with a proven track record and to work on a topic that will constantly challenge you?

We are happy to receive your application with reference:

D ONE Value Creation AG

Sihlfeldstrasse 58

8003 Zürich

• An uncomplicated and low noise environment that enables to focus on what matters most.
• An international team of talented people from diverse backgrounds that have ambitions, always enjoy an additional challenge, and know how to have fun at work.
• Direct mentoring by senior D ONE consultants, plus access to our D ONE Academy including knowledge sharing sessions, expert and working groups.
• A clearly scoped topic that is yours to own, with the freedom to shape how you approach it.
• Frequent offsite socialising events.
• A realistic path to joining D ONE as a consultant after a successful internship.