Internship: LLM-Based Document Information Extraction

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

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.