Internship - LLM-Based Information Extraction (Zurich, Switzerland)

D One; Zürich; On-site; CHF 20,000 - 31,000; Full time

Job summary

D ONE in Zürich offers a fixed-term internship (typically 3 months) at 80–100%. You will work independently on a project in automated understanding of business documents, moving from raw documents to structured, verifiable information.

You will review extraction methods, design pipelines in Python, build annotated data sets, and present findings to technical and non-technical audiences.

Qualifications

• Enrolled in a Bachelor's, Master's or PhD program in CS, Data Science, or related field.
• Interest in at least one industry domain and curiosity about data value.
• Down-to-earth, pragmatic results-oriented attitude.
• Experience working with large data sets and databases.
• Knowledge of Python, SQL, Git, Spark, and cloud platforms.
• Excellent English communication; German is a strong plus.

Responsibilities

• Review information extraction approaches for unstructured and semi-structured documents.
• Design and implement extraction pipelines in clean, modular 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 a technical and non-technical audience.

Skills

Python

SQL

Git

Spark

Cloud platforms

English communication

German (advantage)

Education

Enrolled in Bachelor's/Master's/PhD program

Tools

docling

unstructured

PyMuPDF

Tesseract

Azure Document Intelligence

Job description

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.

Your tasks will include:

• 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.

What you bring:

• 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.

Preferred qualifications:

• 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.

What we offer:

• 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.

To be successful in this role you will need to:

• 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?