Data / Retrieval Engineer

NTT
Gurugram
Workplace: OnsiteFull timeFunction: Software EngineeringExperience: 7+ yearsSkills: ["Analytical","Problem-solving","Communication"]

Design, build, and operate enterprise ingestion and retrieval capabilities for AI agents and knowledge-search platforms. Transform business knowledge into secure, trustworthy, citation-backed context by improving retrieval quality, grounding, data readiness, latency, and operational cost across RAG and enterprise search. Own ingestion pipelines, indexing (vector/keyword/hybrid), access-aware retrieval, evaluation datasets, and production monitoring/runbooks to prevent drift and access-control issues.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
NTT
NTT
1 week ago

Data / Retrieval Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 21 hours agoStatus: Live

Job Summary

Design, build, and operate enterprise ingestion and retrieval capabilities for AI agents and knowledge-search platforms. Transform business knowledge into secure, trustworthy, citation-backed context by improving retrieval quality, grounding, data readiness, latency, and operational cost across RAG and enterprise search. Own ingestion pipelines, indexing (vector/keyword/hybrid), access-aware retrieval, evaluation datasets, and production monitoring/runbooks to prevent drift and access-control issues.
Location: Gurugram
Workplace: Onsite
Employment Type: Full time
Job Function: Software Engineering
Seniority: Mid level

Key Responsibilities

  • •Own the data ingestion and retrieval ecosystem supporting enterprise AI agents.
  • •Design and build scalable ingestion pipelines for structured, semi-structured, and unstructured data and implement chunking, embedding generation, metadata enrichment, and indexing strategies.
  • •Develop retrieval improvements including reranking, grounding, and citation-generation to enhance accuracy and traceability.
  • •Implement access-aware retrieval using user roles/entitlements and source-system permissions, including metadata filtering and freshness/lineage controls.
  • •Create and track retrieval-quality evaluation datasets and metrics (e.g., Recall@K, Precision@K, MRR, NDCG, citation accuracy) and provide monitoring dashboards, alerts, and runbooks to address production issues.

Key Requirements

  • •7+ years of experience in data engineering, backend engineering, search engineering, machine learning engineering, or knowledge-platform development.
  • •Hands-on Python and SQL experience.
  • •Production experience implementing Retrieval-Augmented Generation (RAG) or enterprise-search solutions.
  • •Strong understanding of vector databases, enterprise-search platforms, embedding models, chunking, and keyword/semantic/hybrid retrieval with reranking and metadata management.
  • •Experience implementing role-based/attribute-based access controls and understanding data security, privacy, lineage, and governance.
Experience:7+ yearsRAGEnterprise searchKnowledge-platformsAI agents
Skills:AnalyticalProblem-solvingCommunication
Tech Stack:PythonSQLAPIsETL/ELTRAGEmbeddingsVector searchHybrid searchRerankingGroundingCitationsVector databasesRelational databasesDocument databasesEnterprise searchKeyword searchSemantic searchMetadata filteringData lineageMonitoring

Company Brief

NTT
Dimension Data, operating under NTT Ltd, provides managed IT services, cloud and data center solutions, networking, cybersecurity, and digital transformation services to enterprise customers worldwide.
Industry: Professional Services
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Established Company
Valuation: Public Company (Market Cap in USD)
Headquarters: London, United Kingdom
Founded: 1983
WebsiteLinkedIn