Expert Data Engineer
HybridBengaluru, Karnataka, India
Job Summary
Own AI-ready data engineering by translating product needs into data requirements, pipelines, and knowledge assets that support RAG, agents, and analytics. Build and manage governed data products for domains like client, finance, and risk, ensuring they are complete, accurate, and reusable across business units. Engineer document ingestion, parsing, and indexing processes to prepare policies and operational knowledge for safe AI retrieval while preventing sensitive data leakage. Establish automated data quality rules, monitor freshness and lineage, and define access controls to ensure AI products use only trusted, permissioned data. Partner with product, security, and MLOps teams to resolve quality issues, manage metadata catalogs, and support continuous improvement from production feedback.
Required Qualifications
- Data pipeline engineering
- Data product development
- Data modeling and domain modeling
- ETL/ELT design and orchestration
- API and event-driven data integration
- Data quality rule design and monitoring
- Metadata management and cataloging
- Data lineage and traceability
- Master and reference data awareness
- Data access control and sensitive data handling
- Cloud data platforms and lakehouse/warehouse patterns
- Retrieval-augmented generation data preparation
- Document ingestion and knowledge processing
- Chunking, embeddings, vector stores, and semantic retrieval
- Grounding datasets and evaluation datasets
- Dataset versioning for model, prompt, and retrieval evaluation
- Data preparation for AI agents and copilots
- Data freshness, retrieval quality, and source governance
- AI data observability and feedback loops
- Permission-aware retrieval design
- Prevention of sensitive data leakage through AI systems
- Ability to translate business and product needs into data requirements
- Strong understanding of data ownership and stewardship
- Ability to explain data quality and lineage issues to business leaders
- Strong collaboration with product, AI, architecture, security, and risk teams
- Practical judgment on what data needs to be centralized, federated, reused, or governed locally
- Strong problem-solving around incomplete, conflicting, or low-quality data
- Ability to build reusable capabilities rather than one-off data extracts
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.