Job Summary

As a Document AI Engineer, you will develop intelligent document processing solutions that transform unstructured content into structured, business-ready information. You will leverage OCR, computer vision, machine learning, NLP, and LLM technologies to automate classification, extraction, validation, and quality scoring processes.

Responsibilities

- Build document classification and extraction models using OCR and AI technologies.
- Develop document processing pipelines for ingestion, validation, enrichment, and workflow routing.
- Implement confidence scoring, completeness analysis, and document quality validation.
- Configure source-evidence linking, citation tracing, and lineage capabilities.




- Optimize extraction accuracy and model performance using training and validation datasets.
- Collaborate with AI, integration, and business teams to enhance document automation workflows.

Skills & Experience

- 5+ years of experience with OCR, Document AI, Intelligent Document Processing, or NLP solutions.
- Experience with Azure Document Intelligence, ABBYY, AWS Textract, Google Document AI, or similar platforms.
- Solid Python programming experience.
- Experience with LLMs, embeddings, and AI-assisted document processing.
- Knowledge of machine learning pipelines, model validation, and performance tuning.

📌 Document AI Engineer (Pune)
🏢 marlabs
📍 Pune