LLM-Driven Information Extraction Internship

D ONE – Data Driven Value Creation; Zürich; On-site; CHF 20,000 - 27,000; Full time

Job summary

D ONE – Data Driven Value Creation in Zürich is seeking an enthusiastic student for a fixed-term internship focused on automated understanding of business documents. You will work independently to move from raw documents to structured, verifiable information and ensure the approach holds across domains.

You will design extraction pipelines, annotate data, and measure quality while dealing with layouts, languages, scan quality and edge cases.

Qualifications

• Enrolled in a Bachelor's/Master’s/PhD programme in CS, Data Science, Computational Linguistics, Engineering, Mathematics or comparable field.
• Interest in an industry domain and curiosity about how data creates value.
• Down-to-earth, pragmatic, results-oriented attitude.
• Experience with large data sets and databases.
• Knowledge of Python, SQL, Git, Spark, cloud platforms.
• Excellent communication in English; German is a strong plus.
• Solid NLP foundations, including NER, relation extraction and text classification.
• Familiarity with document parsing and OCR tooling and layout-aware models.

Responsibilities

• Review current approaches to information extraction from 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 a non-technical audience.

Skills

Python

SQL

Git

Spark

Cloud platforms

English communication

German language (plus)

Education

Bachelor’s/Master’s/PhD student in CS/DS/CL/Engineering/Math

Tools

Python

SQL

Git

Spark

Cloud platforms

Job description

D ONE – Data Driven Value Creation in Zürich is seeking an enthusiastic student for a fixed-term internship focused on automated understanding of business documents. You will work independently to move from raw documents to structured, verifiable information and ensure the approach holds across domains.

You will design extraction pipelines, annotate data, and measure quality while dealing with layouts, languages, scan quality and edge cases.