Senior Document Processing Engineer - OCR & Data Extraction

Glocomms; New York (NY); On-site; USD 140,000 - 175,000; Full time

Job summary

Glocomms is hiring a Senior Software Engineer focused on document processing, OCR, and data extraction quality. You will own mission-critical systems that transform complex, unstructured documents into reliable data for AI-powered workflows across OCR, document understanding, and extraction pipelines.

You will collaborate with AI engineers to improve extraction accuracy and support workflow automation, with emphasis on reliability, performance, and edge-case handling in regulated environments.

Qualifications

• 5+ years of software engineering experience.
• Production-grade document processing, OCR, extraction, or data systems experience.
• Strong backend fundamentals and problem-solving skills.
• Experience with unstructured data formats like PDFs, images, or spreadsheets.
• Ownership mindset and ability to work independently.

Responsibilities

• Build and enhance OCR and document extraction systems.
• Design pipelines for processing PDFs, spreadsheets, images, and unstructured documents.
• Improve extraction accuracy, reliability, and performance in production.
• Develop validation frameworks and confidence scoring for extracted data.
• Collaborate with AI engineers to enable document-derived data for ML workflows.
• Investigate extraction failures and continuously improve quality.
• Build tooling to monitor document processing performance.
• Support workflow automation reliant on high-quality document understanding.

Skills

Backend engineering

Document processing

OCR systems

Data extraction

Debugging

Job description

Glocomms is hiring a Senior Software Engineer focused on document processing, OCR, and data extraction quality. You will own mission-critical systems that transform complex, unstructured documents into reliable data for AI-powered workflows across OCR, document understanding, and extraction pipelines.

You will collaborate with AI engineers to improve extraction accuracy and support workflow automation, with emphasis on reliability, performance, and edge-case handling in regulated environments.