About the role

We are looking for a Data Scientist

to join an international project focused on developing and improving AI-powered document processing solutions.

In this role, you will work with LLMs, Vision-Language Models, OCR, NLP and Machine Learning

to transform complex unstructured business documents into structured data.

You will collaborate with AI Engineers, Data Engineers, Product teams and business stakeholders to develop and evaluate solutions that deliver measurable business value.

If you enjoy solving complex Data Science challenges and experimenting with AI to solve real business problems, this could be your next challenge!

What you'll do

Design and improve AI solutions for document extraction, classification, validation and transformation.

Experiment with LLMs, multimodal models, OCR, NLP and Machine Learning

to identify the best approach for each use case.

Develop prompts, structured outputs, validation and post-processing logic for complex document formats.

Build datasets and evaluation frameworks to measure accuracy and continuously improve solution performance.

Develop automated evaluations and regression tests to ensure robustness when models or pipelines change.

Write clean, reusable Python

code and translate successful experiments into production-ready solutions with AI and Data Engineers.

Work with Product and business stakeholders to define use cases, success criteria and measurable AI solutions.

3+ years of experience

in Data Science, Machine Learning or Applied AI.

Hands‑on experience with LLMs and Generative AI ,



including prompt engineering and experimentation.

Strong understanding of NLP, Machine Learning and statistics , including when classical or deterministic approaches are more appropriate than LLMs.

Experience working with unstructured or semi‑structured data , datasets, ground truth and evaluation metrics.

Strong Python

skills and good practices around testing, version control and reproducible experimentation.

Experience analysing results and translating findings into measurable improvements.

Fluent English

and spanish and ability to communicate technical concepts to both technical and non‑technical stakeholders.

Degree in Computer Science, AI, Data Science, Mathematics, Engineering or a related field.

Experience with Document Intelligence and OCR , particularly Azure Document Intelligence .

Experience with managed AI platforms such as Azure OpenAI

or Amazon Bedrock .

Experience with document classification, information extraction or NER .

Experience applying multimodal or Vision‑Language Models

to document content and layouts.

Hybrid model – 2 days on site per week

Why join this project?

People first





– diverse and inclusive culture in an international environment .

Work on high‑impact Data & Insights initiatives

across business performance , operations , finance , and commercial domains .

Help shape how data supports strategic decision-making

across a large international organisation .

Explore the evolution of AI-driven analytics , productivity tools , and data discoverability .

Contribute to self‑service analytics , data products , and scalable reporting practices .

Work closely with business

and senior stakeholders , turning complex data

into meaningful insights .

High team stability

and collaborative culture .

€1200 per year training budget

and continuous learning opportunities .

Private health insurance

and benefits package .

Flexible working hours

and hybrid model .

Wellhub : fitness, wellness, and mental health support.

Football and paddle tennis teams sponsored by Capitole .

Team buildings , general events , and strong tech communities .

Curious about our culture? Check out what people are saying about us on Glassdoor.

We know that not every candidate will meet 100% of the requirements. If your profile doesn’t match perfectly but you believe you can add value, we’d still love to hear from you.

Information Security Notice

The employee will have access to confidential information related to Capitole and the assigned project.

Compliance with internal security and information protection policies is mandatory.

#J-18808-Ljbffr

📌 DATA SCIENTIST – DOCUMENT INTELLIGENCE (Barcelona)
🏢 Capitole
📍 Barcelona