Data Scientist - Mid
Core
Design and implement Intelligent Document Processing (IDP) and AI solutions to automate data extraction and enrichment for insurance claims.
Role type
Mid-level data scientist (IDP & AI)
Builds
Automated document extraction and data enrichment workflows for insurance claims
Domain
Insurance / Intelligent Document Processing / AI/ML
Deliverable
production ML models | product features
Required skills
Python, SQL, Git, data manipulation, data extraction, manual data labeling, NLP, decision trees, clustering, evaluation metrics (precision, recall, F1)
Preferred skills
OCR, image analytics, cloud technologies, IDP software configuration, experimental design
Technologies
Python, SQL Server, Git, OCR, NLP, generative AI
Responsibilities
Translate business problems into technical solutions for automated document extraction; manipulate data and develop ad hoc queries; manually label and validate training datasets; implement evaluation frameworks using precision, recall, F1 scores; build predictive models using machine learning techniques; create technical documentation; monitor and evaluate solution performance.
Seniority
Mid-level, hands-on IC

