Senior Data / Ingestion Engineer (Optical Character Recognition (OCR) systems intergrations) (вакансія неактивна)

We’re a global IT consulting company and a software development service provider that helps organizations operate at their best. With 30+ years of experience, +6 Global locations, and +1000 employees, TEAM combines technology expertise, valuable insights, business intelligence, and a client-centered approach to address challenges in business operations, digital transformation, risk management, compliance, business continuity, and more.

Our client is delivering AI-driven transformation initiatives for leading insurance organizations, helping them modernize business processes, automate complex workflows, and introduce intelligent AI capabilities into existing operations and customer-facing solutions.

The project brings together business transformation, insurance domain expertise, and advanced AI technologies. As part of the team, you will work closely with insurance stakeholders and technical delivery squads to identify valuable AI opportunities and translate complex business needs into solutions that can be successfully designed, developed, and implemented.

We are looking for Senior data engineer focused on building robust data ingestion pipelines and integrating Optical Character Recognition (OCR) systems. Specializes in extracting structured data from unstructured insurance documents.

Responsibilities

• Design and implement scalable data pipelines for ingesting high-volume unstructured insurance documents (PDFs, scans, emails)
• Integrate, configure, and optimize OCR and document parsing technologies to extract high-accuracy text and layouts
• Build automated workflows for text cleaning, normalization, semantic chunking, and metadata tagging
• Design vector storage data schemas and robust retrieval mechanisms (RAG) to feed downstream AI models
• Ensure document processing pipelines comply with enterprise security and low-latency SLA requirements
• Build automated error-monitoring and extraction validation loops to continuously flag low-confidence OCR outputs
• Experience building data processing and document ingestion pipelines on public cloud platforms is required; Azure, AWS, and Databricks experience strongly preferred

Requirements

• Python, SQL, AWS (S3, Step Functions, CloudWatch)
• Experience processing unstructured documents (PDF, Word, Excel, PPT), building connectors to SharePoint, emails
• Experience with vector DBs / RAG a plus
• Development best practices — Git, CI/CD, testing
• Document extraction/OCR tools (e.g., AWS Textract or equivalent)

What We Offer

At TEAM International, you’ll have the opportunity to work on impactful projects alongside top professionals, collaborate with international clients, and leverage the latest technologies.

• Work with global IT talent in a flexible engagement model
• Be part of challenging, high-impact projects with modern tech stacks
• Full compliance with security and regulatory standards
• A supportive, collaborative, and people-first environment