AI Data 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

We’re looking for a Data Scientist to help build and improve AI‑powered document processing solutions used across a large, complex organisation. You’ll work across LLMs, multimodal models, OCR, NLP and classical ML to turn messy, unstructured business documents into reliable structured data that drives real value.

In this role, you’ll design and evaluate approaches for document extraction, classification and validation — “Design, prototype and evaluate approaches for document extraction, classification, validation and transformation.” You’ll also work with highly variable formats — “Work with complex and variable formats, including multi‑page documents, tables, line items and inconsistent layouts.”

What you’ll do

• Develop and optimise prompts, structured outputs, validation logic and post‑processing components.
• Compare LLMs, multimodal models, OCR and deterministic approaches to select the right solution for each use case.
• Build representative datasets, define ground truth and establish robust evaluation metrics.
• Run experiments, analyse failure patterns and iterate to improve accuracy and reliability.
• Create reproducible Python workflows and contribute reusable components for extraction, validation and data prep.
• Collaborate with Product, AI Engineering and business teams to translate requirements into measurable data science problems.
• Communicate findings clearly to both technical and non‑technical audiences.

What you’ll bring

• 3+ years in data science, machine learning or applied AI.
• Hands‑on experience with LLMs, prompt engineering and experimentation.
• Strong NLP/ML fundamentals and the judgement to know when classical methods outperform LLMs.
• Solid statistics — enough to judge whether a performance change is real.
• Experience with unstructured or semi‑structured documents.
• Python skills that make your work reproducible and easy for engineers to productionise.
• Ability to explain technical trade‑offs clearly.
• Comfortable diving into business domains to understand what “correct extraction” actually means.

Nice to have

• Experience with managed AI platforms (Azure OpenAI, Amazon Bedrock).