[Remote] Data Scientist – OCR & Document Digitization

Note: The job is a remote job and is open to candidates in USA. Bellatrix Systems LLC is seeking a Data Scientist to develop and improve production OCR-based document digitization solutions. The role focuses on extracting and validating information from handwritten documents and poor-quality faxes, evaluating OCR technologies, and improving workflows to reduce fax-related costs and increase operational efficiency.

Responsibilities

• Develop, deploy, and maintain production OCR solutions to digitize incoming faxes and improve document processing
• Process handwritten documents, poor-quality faxes, and image artifacts while improving extraction accuracy and validating data
• Evaluate LLMs, cloud-based OCR services, and traditional OCR tools to identify suitable technical solutions
• Analyze existing fax-related workflows, identify why providers continue sending faxes, and recommend process or vendor improvements to reduce costs
• Collaborate with technical and business stakeholders to explain solution trade-offs, gain alignment, and drive business decisions
• Take ownership of end-to-end project delivery, leveraging existing solutions and working closely with team members to achieve measurable business outcomes
• Develop, deploy, and maintain production OCR solutions to digitize incoming faxes and improve document processing
• Process handwritten documents, poor-quality faxes, and image artifacts while improving extraction accuracy and validating data
• Evaluate LLMs, cloud-based OCR services, and traditional OCR tools to identify suitable technical solutions
• Analyze existing fax-related workflows, identify why providers continue sending faxes, and recommend process or vendor improvements to reduce costs
• Collaborate with technical and business stakeholders to explain solution trade-offs, gain alignment, and drive business decisions
• Take ownership of end-to-end project delivery, leveraging existing solutions and working closely with team members to achieve measurable business outcomes

Skills

• 5+ years of relevant Data Science experience
• Strong hands-on experience with Optical Character Recognition (OCR)
• Experience with LLM-based OCR, cloud OCR tools, and traditional OCR technologies such as Tesseract
• Experience processing handwritten documents, poor-quality faxes, and image artifacts
• Experience with database validation and improving data extraction accuracy
• Strong programming skills in Python and SQL
• Familiarity with Google Cloud Platform (GCP)
• Experience developing, deploying, and maintaining production applications
• Strong understanding of OCR tool limitations, data quality challenges, and improvement strategies
• Excellent stakeholder communication and business understanding
• Ability to explain technical trade-offs and gain buy-in from business stakeholders
• Experience collaborating with technical and nontechnical teams
• Demonstrated end-to-end ownership of complex or ambiguous projects with limited supervision
• Strong technical judgment, problem-solving skills, and an outcome-oriented mindset
• Growth mindset and ability to build upon existing solutions rather than starting from scratch

Benefits

• Remote (Chicago, IL, or New York, NY candidates preferred)

Company Overview

Company H1B Sponsorship