Senior Python Data Engineer (OCR & Document Processing)- remote

Inetum Romania

6d•Remote

About The Position

Inetum is a European leader in digital services. For businesses, public sector organizations, and society as a whole, the group’s 26,000 consultants and specialists work every day to create tangible digital impact: solutions that contribute to performance, innovation, and the common good. With a presence in 19 countries, working closely with local communities, and alongside its major software developer partners, Inetum supports organizations in their digital transformation challenges with proximity, flexibility, and responsibility. Driven by its purpose, Inetum champions a vision of technology that is useful and well-managed, capable of unlocking the full potential of organizations and society: “Let’s make tech right.” In 2025, the group generated revenue of 2.2 billion euros. More information at: www.inetum.com Mission Design, build, and optimize scalable data ingestion and document processing solutions that transform large volumes of unstructured insurance data into structured, AI-ready information. Enable downstream AI and retrieval systems by leveraging OCR, document intelligence, vector databases, and cloud-native data pipelines.

Requirements

5-10 years of experience in Data Engineering, Data Processing, Document Intelligence, or related fields.
Proven experience building scalable data ingestion and processing pipelines.
Experience working with large volumes of unstructured and semi-structured data.
Experience designing cloud-based data solutions.
Strong programming skills in Python.
Strong SQL knowledge.
Hands-on experience with AWS services, including: S3 Step Functions CloudWatch
Experience processing unstructured documents such as: PDF Word Excel PowerPoint Email content
Experience building connectors and integrations with enterprise content repositories (e.g., SharePoint).
Experience with OCR and document extraction tools (AWS Textract or equivalent).
Experience designing and implementing data ingestion and transformation pipelines.
Familiarity with vector databases and Retrieval-Augmented Generation (RAG) concepts.
Experience with software development best practices: Git CI/CD Automated testing

Nice To Haves

Experience with Vector Databases.
Experience with RAG architectures and AI/LLM-based applications.
Experience with Azure cloud services.
Experience with Databricks.
Experience in Insurance, Banking, or other regulated industries.

Responsibilities

Design and implement scalable data ingestion pipelines for processing high volumes of unstructured documents, including PDFs, scans, emails, and Office files.
Integrate, configure, and optimize OCR and document extraction technologies to maximize text extraction accuracy and document understanding.
Build automated workflows for document parsing, text cleaning, normalization, semantic chunking, and metadata enrichment.
Develop connectors and integrations for document sources such as SharePoint, email systems, and enterprise repositories.
Design and maintain vector database schemas and retrieval mechanisms to support Retrieval-Augmented Generation (RAG) solutions and AI applications.
Ensure document processing pipelines meet enterprise security, compliance, performance, and availability requirements.
Implement monitoring, validation, and quality-control mechanisms to identify and manage low-confidence OCR and extraction results.
Optimize data processing workflows for scalability, reliability, and low-latency operations.
Collaborate with AI Engineers, Backend Engineers, and Platform teams to deliver end-to-end AI-powered document processing solutions.
Develop and maintain cloud-native data ingestion solutions on public cloud platforms.