Data Engineer

Apply now »

Date: Nov 16, 2026

Location: Bangalore, KA, IN

Company: NTT DATA Services

"Position Overview
We are seeking an experienced Databricks Data Engineer to design and enhance enterprise document-processing and data-extraction solutions. The role will focus on ingesting structured and unstructured content, extracting business and policy information using LLM-based approaches, improving extraction accuracy, and making validated information available to downstream applications through an ontology-driven data layer.
The engineer will join a small, hands-on team working on document intelligence solutions supporting brokerage and underwriting workflows. A major focus will be redesigning existing pipelines to improve accuracy, performance, scalability, and maintainability while supporting a broader migration from Microsoft Fabric to Databricks.
Key Responsibilities
•                     Design, build, and optimize Databricks data pipelines for document ingestion, classification, extraction, validation, and downstream consumption.
•    Process information from multiple document and communication formats, including:
o        PDF documents
o    Emails and attachments
o    Excel/XLSX files
o    Insurance applications
o    Statements of Values (SOVs)
o    Other structured and unstructured documents
•    Improve existing extraction pipelines where LLMs produce false positives, incorrect metadata, or inaccurate field values.
•    Develop validation and quality-control approaches that improve the reliability of extracted information.
•    Implement document classification and content-aware extraction strategies.
•    Handle source-specific extraction rules, such as extracting particular attributes from an email rather than from attached documents.
•    Design pipelines that transform extracted information into consistent, structured JSON outputs for downstream applications.
•    Contribute to the design and implementation of a custom ontology layer that represents key insurance business entities and relationships.
•    Map extracted information into the ontology so applications can consume standardized business concepts rather than raw document fields.
•    Address performance challenges associated with processing large or complex Excel/XLSX and SOV files.
•    Optimize pipeline scalability and concurrency for production workloads.
•    Work with PostgreSQL/Lakebase-based persistence for final structured outputs.
•    Collaborate closely with brokerage, underwriting, AI, and data engineering teams to connect extracted application data with downstream underwriting processes.
Required Qualifications
•                     Strong hands-on experience with Databricks and production data engineering.
•    Strong proficiency in Python, PySpark, and SQL.
•    Experience building scalable ingestion and transformation pipelines on the Databricks platform.
•    Experience processing unstructured and semi-structured data, particularly PDFs, emails, Excel files, JSON, and business documents.
•    Experience integrating LLMs or AI models into data-processing pipelines.
•    Understanding of prompt-based and structured data extraction from documents.
•    Experience implementing data validation, reconciliation, or quality controls for AI-generated outputs.
•    Strong understanding of data modeling, metadata, schemas, entity relationships, and semantic/ontology concepts.
•    Experience designing APIs, JSON structures, or data products for downstream application consumption.
•    Experience troubleshooting performance, scalability, and concurrency issues in production data pipelines.
•    Experience working with cloud-based data architectures.

Minimum 7+ years of experience in data engineering, software development, or production data pipeline development.
Minimum 4+ years of hands-on experience with Databricks and scalable data-processing pipelines."


Job Segment: Database, Cloud, SQL, Technology

Apply now »