Information Extraction Specialist

About the role

We are looking for an Information Extraction Specialist to lead the design and delivery of robust extraction pipelines that turn unstructured documents into structured, actionable data. The role is fully remote, allowing you to work with global teams and diverse data sources.

Key responsibilities

• Design, develop, and maintain end‑to‑end information extraction pipelines for varied document types such as legal contracts, medical records, financial reports, news articles and technical manuals.
• Create and manage high‑quality training datasets, define sampling strategies, lead annotation teams and ensure rigorous quality assurance.
• Evaluate model performance using precision, recall, F1 and other metrics; analyse errors and iterate on guidelines, data or model architecture.
• Assess, integrate and customise open‑source and commercial extraction tools and platforms.
• Write scripts and automated workflows to streamline data processing and pipeline operations.
• Rapidly acquire domain knowledge to adapt extraction systems to new industries or document formats.

Required profile

• Minimum 5 years of professional experience in information extraction, NLP or computational linguistics.
• Strong proficiency in Python for data analysis and NLP tasks.
• Hands‑on experience with NLP libraries such as spaCy, NLTK, Hugging Face Transformers or Stanford CoreNLP.
• Proven ability to design annotation schemas and clear extraction guidelines.
• Deep understanding of evaluation methodologies and metric interpretation.
• Excellent written and verbal communication in English.

Required skills

• Python
• spaCy
• NLTK
• Hugging Face Transformers
• Stanford CoreNLP