AI-powered Document Intelligence Scientist

Capitole; Cataluña; Híbrido; EUR 55.000 - 75.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Training budget €1200/year

Private health insurance

Hybrid model

Flexible hours

Descripción de la vacante

Capitole is seeking a Data Scientist to join an international project focused on AI-powered document processing. You will work with LLMs, OCR, NLP and ML to transform unstructured business documents into structured data, collaborating with AI Engineers, Data Engineers, Product teams and business stakeholders.

In this role you will design and evaluate AI solutions, develop production-ready code in Python, and help drive measurable business value across a large organization.

Formación

• 3+ years of experience in Data Science, ML or Applied AI.
• Hands-on with LLMs and Generative AI, including prompt engineering.
• Strong NLP, ML and statistics knowledge; know when classical approaches suit best.
• Experience with unstructured data, ground truth and evaluation metrics.
• Strong Python skills, testing and reproducible experiments.

Responsabilidades

• Design and improve AI solutions for document extraction, classification and transformation.
• Experiment with LLMs, multimodal models, OCR, NLP and ML for each use case.
• Develop prompts, outputs, validation, and post-processing for complex formats.
• Build datasets and evaluation frameworks to measure accuracy and improve performance.
• Develop automated evaluations and tests to ensure robustness when pipelines change.
• Write clean Python code and translate experiments into production-ready solutions.
• Collaborate with Product and business stakeholders to define use cases and success criteria.

Conocimientos

LLMs & Gen AI

Python

NLP

Statistical analysis

Stakeholder comms

Bilingual EN/ES

Educación

Degree in CS/AI/Data Science/Engineering

Master's preferred

Herramientas

Azure Document Intelligence

Azure OpenAI

Amazon Bedrock

OCR

Descripción del empleo

Capitole is seeking a Data Scientist to join an international project focused on AI-powered document processing. You will work with LLMs, OCR, NLP and ML to transform unstructured business documents into structured data, collaborating with AI Engineers, Data Engineers, Product teams and business stakeholders.

In this role you will design and evaluate AI solutions, develop production-ready code in Python, and help drive measurable business value across a large organization.