AI Document Extraction Scientist

SustainRecruit Talent; Barcelona; Presencial; EUR 45.000 - 65.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Azure OpenAI

Amazon Bedrock

Descripción de la vacante

SustainRecruit Talent seeks a Data Scientist to build and improve AI-powered document processing across a large organization. You will work with LLMs, multimodal models, OCR, NLP and classical ML to transform messy documents into reliable structured data.

You’ll design extraction and classification approaches, handle multi-page formats, and collaborate with Product and AI Engineering to translate requirements into measurable data science problems.

Formación

• 3+ years in data science, ML or applied AI.
• Hands-on with LLMs, prompts and experimentation.
• Strong NLP/ML fundamentals and solid statistics.
• Experience with unstructured or semi‑structured documents.
• Python for reproducible workflows and productionisation.
• Ability to explain technical trade-offs clearly.
• Comfort with translating business needs into data problems.

Responsabilidades

• Design and optimize prompts, outputs, validation logic and post-processing.
• Compare LLMs, multimodal models and OCR to pick the right approach.
• Build datasets, define ground truth and evaluation metrics.
• Run experiments and analyse failure patterns to improve accuracy.
• Create reproducible Python workflows and reusable components.
• Collaborate with Product, AI Eng and business teams to translate requirements.

Conocimientos

Python

LLMs

NLP

Statistics

Unstructured data

Prompt engineering

Explain trade-offs

Business domain

Herramientas

PyTorch

Scikit-learn

Descripción del empleo

SustainRecruit Talent seeks a Data Scientist to build and improve AI-powered document processing across a large organization. You will work with LLMs, multimodal models, OCR, NLP and classical ML to transform messy documents into reliable structured data.

You’ll design extraction and classification approaches, handle multi-page formats, and collaborate with Product and AI Engineering to translate requirements into measurable data science problems.