Data & Search Engineer

About This Role

Role Overview

We are seeking a Data & Search Engineer to design, build, and operate scalable data ingestion and retrieval systems supporting advanced AI-driven use cases. This role is critical in ensuring high-quality document processing, indexing, and search relevance across structured and unstructured data sources.

Key Responsibilities

• Design and implement data ingestion pipelines for structured and unstructured data sources
• Develop and optimize document chunking and enrichment strategies (identifiers, metadata, topics)
• Ensure data quality, consistency, and masking across ingestion workflows
• Build and maintain search indexes with a focus on performance and scalability
• Implement and optimize hybrid search (semantic + keyword) capabilities
• Design metadata schemas to enhance search relevance and filtering
• Conduct retrieval relevance evaluation and continuously improve ranking quality
• Monitor and validate index and chunk performance
• Collaborate with AI/ML teams to support RAG (Retrieval-Augmented Generation) use cases

Required Qualifications

• Strong experience in data engineering, search platforms, or information retrieval systems
• Hands-on experience with search technologies (e.g., Elasticsearch, OpenSearch, Azure Cognitive Search)
• Experience with semantic search and vector-based retrieval
• Proficiency in data pipeline development (Python, Spark, or similar)
• Solid understanding of metadata design and indexing strategies
• Experience in data masking and governance practices
• Familiarity with retrieval evaluation metrics (precision, recall, ranking quality)

Preferred Qualifications

• Experience supporting AI/LLM-based systems
• Knowledge of document processing pipelines (OCR, parsing, enrichment)
• Exposure to large-scale enterprise data environments