Data Scientist (Predictive Modeling)

Strategic Analytics is a growing team at Arch focused on delivering data-driven solutions that improve business performance. We develop intelligent data automation capabilities that combine external data with Intelligent Document Processing (IDP) and AI/ML technologies to extract and structure information from unstructured sources.

In this role, you will support the design and implementation of IDP and AI solutions across claims. This includes preparing data for document processing, transforming outputs into structured datasets, and contributing to automated document extraction and data enrichment workflows.

You will collaborate with business stakeholders, engineers, and data scientists to translate business problems into technical solutions.

Responsibilities

• Collaborate with business customers and engineers to translate business problems into technical solutions and deliver automated document extraction and data enrichment solutions.
• Manipulate data using Python and SQL Server; develop ad hoc queries to investigate data anomalies and to summarize data for pattern detection.
• Manually label and validate training datasets.
• Under supervision use AI technologies such as natural language processing to extract business data from unstructured and semi-structured sources (e.g., loss history reports, insurance applications, claim files, application scraping using OCR/ generative AI, etc.).
• Create technical documentation to archive end-to-end processes.
• Implement evaluation frameworks using precision, recall, F1 scores, accuracy, and operational metrics
• Build solutions to monitor and continuously evaluate performance of implemented solutions.
• Collaborate with experienced modelers to build predictive models and analytic solutions; apply machine learning techniques such as decision trees and clustering.

Qualifications

• Experience in manipulating, processing and extracting value from datasets
• Exposure to data science, software development, engineering or equivalent
• Detail-oriented with strong organizational skills
• Strong critical thinking skills to tackle complex data challenges
• Strong communication skills that convey statistical and business impact, proactively surface issues
• Comfortable working in a fast-paced and highly collaborative global team
• Experience in Python, SQL, and Git
• Experience with evaluation frameworks, experimental design
• Experience with OCR, NLP, and/or image analytics
• Experience with cloud technologies and implementing data science/AI solutions.
• Experience configuring & establishing automations utilizing IDP software solutions
• The ideal candidate will have experience working in the insurance industry
• Bachelor’s degree in data science, analytics, statistics, actuarial science, mathematics, engineering or similar quantitative fields; or significant experience in data analytics