Senior Engineer, Intelligent Document Processing

Clark

$120K — $150K *
Information Technology
5 - 7 years of experience
Job Overview by Ladders

Qualifications

  • 5+ years of software engineering experience
  • Experience building production data, document, OCR, or extraction systems
  • Strong backend engineering fundamentals
  • Strong debugging and data quality instincts
  • Experience with PDFs, spreadsheets, images, or unstructured documents
  • Comfortable building systems where correctness and reliability matter
  • Strong ownership and ability to operate independently

Responsibilities

  • Build and improve OCR and document extraction systems
  • Design pipelines for parsing various document types
  • Improve extraction quality, accuracy, and reliability
  • Build validation systems and confidence scoring
  • Partner with AI engineers to enhance data usability
  • Collaborate with Audit Engineers to tackle document edge cases
  • Debug extraction failures and enhance system performance
  • Build tools to monitor and evaluate document processing quality

Benefits

  • Opportunity to enhance critical document processing systems
  • Work directly on improving customer trust and product quality
  • Collaborate with teams in AI and auditing for impactful outcomes
  • Engage with complex document types and workflows
  • Opportunity for independent ownership and initiative in projects
Full Job Description
The Role

We are hiring a Senior Engineer focused on document processing, OCR, and extraction quality for live workpapers.

This role will own critical systems that turn messy customer documents into usable, reliable data for Clark's AI workflows. You will work across OCR, extraction, document understanding, validation, and product workflows that depend on accurate source material.

Why This Role Matters

Audit workflows depend on documents: workpapers, financial statements, trial balances, invoices, confirmations, schedules, screenshots, PDFs, and spreadsheets.

If document processing is unreliable, product quality suffers. This role directly improves extraction accuracy, customer trust, and Clark's ability to support complex audit workflows in production.

What You'll Do
  • Build and improve OCR and document extraction systems
  • Design pipelines for parsing PDFs, spreadsheets, images, and structured/unstructured documents
  • Improve extraction quality, accuracy, and reliability for live customer workflows
  • Build validation systems and confidence scoring around extracted data
  • Partner with AI engineers to make extracted data usable in LLM workflows
  • Partner with Audit Engineers to understand document types and customer edge cases
  • Debug extraction failures and improve system performance over time
  • Build tooling to monitor and evaluate document processing quality
  • Support workpaper automation and evidence review workflows


Who You Are
  • 5+ years of software engineering experience
  • Experience building production data, document, OCR, or extraction systems
  • Strong backend engineering fundamentals
  • Strong debugging and data quality instincts
  • Experience working with PDFs, spreadsheets, images, or unstructured documents
  • Comfortable building systems where correctness and reliability matter
  • Strong ownership and ability to operate independently


Bonus
  • Experience with OCR, computer vision, document AI, or information extraction
  • Experience with LLMs or AI-native document workflows
  • Experience in accounting, audit, financial services, legaltech, insurance, or compliance
  • Experience building evals or quality measurement systems
  • Experience with large-scale document pipelines

Similar Jobs

More Jobs at Clark

More Information Technology Jobs

Find similar Senior Engineer, Intelligent Document Processing jobs: