Senior OCR Engineer: Intelligent Document Processing

Raval West; United States; On-site; USD 90,000 - 130,000; Full time

Job summary

Raval West is seeking an Intelligent Document Processing - OCR Engineer with 3+ years of experience to improve document extraction across 20 document types and template variations, ensuring reliable results from scans, phone photos, and compressed PDFs.

You will build and maintain Python-based OCR pipelines, implement image-quality checks, and collaborate with the forensics engineer to reduce false fraud flags while measuring extraction accuracy by document type.

Qualifications

• 3+ years building or operating production document-processing or OCR systems.
• Hands-on experience with Tesseract, PaddleOCR, Google Document AI, or similar OCR tools.
• Strong Python skills and image preprocessing experience.
• Experience handling inconsistent inputs and testing extraction accuracy.
• Bachelor’s or Master’s degree in CS/Engineering or equivalent.

Responsibilities

• Build and maintain Python-based OCR and extraction pipelines.
• Implement image-quality checks for blur, glare, skew, and compression.
• Collaborate with forensics engineer to reduce false fraud flags.
• Measure extraction accuracy by document type and calibrate confidence scores.
• Automate regression testing for every change.
• Create user guidance for submitting replacement documents.

Skills

OCR systems

Python

Tesseract

PaddleOCR

Google Document AI

Image preprocessing

Deskewing

Denoising

Contrast adjustment

Layout-aware models

Key-value extraction

Education

Bachelor’s or Master’s in CS/Engineering

Tools

OCR tool stack

Job description

Raval West is seeking an Intelligent Document Processing - OCR Engineer with 3+ years of experience to improve document extraction across 20 document types and template variations, ensuring reliable results from scans, phone photos, and compressed PDFs.

You will build and maintain Python-based OCR pipelines, implement image-quality checks, and collaborate with the forensics engineer to reduce false fraud flags while measuring extraction accuracy by document type.