Ey – GDS Consulting - AI and DATA-Semantic Data Engineer-Senior
No salary listed
Senior, Expert
Hyderabad, Telangana, India
In Person
Data & AnalyticsData Engineering
About the job
Requirements
- The role requires 5–10 years of experience in Data Engineering, Data Management, Information Architecture, Semantic Data Engineering, or AI-ready data platform delivery.
- The role requires 2–4+ years of hands-on experience with semantic technologies, ontology implementation, knowledge graphs, graph modelling, or semantic data platforms.
- The role requires strong implementation experience with SQL, Python, PySpark, RDF, OWL, SPARQL, semantic models, metadata engineering, data pipelines, and modern lakehouse architecture.
Responsibilities
- Design and implement semantic data engineering solutions using semantic modelling, ontology implementation, taxonomies, SKOS concepts, and governed semantic layer patterns.
- Translate business concepts and architecture guidance into implementable semantic data structures, reusable semantic mappings, and operational data products.
- Build semantic models that connect business glossaries, metadata, data lineage, data quality rules, and downstream analytics or AI consumption needs.
- Document implementation patterns, naming conventions, mappings, and reusable engineering assets to support adoption of semantic standards.
- Apply conceptual, logical, physical, and dimensional data modelling practices for semantic and analytical use cases.
- Implement entity, relationship, hierarchy, classification, metric, and attribute structures for relational, lakehouse, graph, and semantic layer consumption.
- Support star schema, snowflake schema, domain model, canonical model, and Power BI Semantic Model implementation for analytical consumption.
- Partner with data architects and semantic architects to make data models reusable, governed, explainable, and aligned with enterprise information architecture.
- Build and maintain knowledge graph solutions using graph data modelling, graph relationships, entity resolution patterns, classifications, and hierarchical structures.
- Implement semantic graph pipelines using RDF, OWL, SPARQL, and knowledge graph platforms such as Neo4j, Amazon Neptune, and GraphDB.
- Integrate structured, semi-structured, and unstructured data into semantic ecosystems and knowledge graph foundations.
- Support GraphRAG, semantic search, enterprise search, vector search, and AI-driven knowledge retrieval use cases.
- Develop data integration pipelines using SQL, Python, PySpark, ETL/ELT patterns, APIs, enterprise data integration, and metadata-driven engineering patterns.
- Build semantic data pipelines across lakehouse architecture, data platforms, semantic layers, knowledge graph platforms, and AI-ready data products.
- Engineer reliable data flows for business glossaries, metadata management, lineage capture, semantic mappings, graph loading, and data quality validation.
- Collaborate with platform teams to implement scalable and maintainable semantic data products across lakehouse, warehouse, and graph ecosystems.
- Prepare AI-ready data products that improve LLM grounding, contextual retrieval, semantic search, and explainability for AI and GenAI use cases.
- Support GraphRAG, RAG, vector search, semantic search, enterprise search, and intelligent agent patterns using trusted semantic data foundations.
- Partner with AI engineering teams to make semantic data assets usable for retrieval, contextual reasoning, and AI-enabled data discovery.
- Contribute to agentic AI patterns in which semantic metadata, knowledge graphs, and governed data products support autonomous discovery or insights workflows.
- Implement metadata management, data governance, data lineage, data quality, access controls, and semantic governance integrations using tools such as Microsoft Purview, Unity Catalog, and Immuta.
- Apply Git, CI/CD, DevOps, documentation, testing, and release practices for semantic data pipelines, ontology assets, graph mappings, and generated artefacts.
- Support Data SRE and observability practices for semantic pipelines, graph loads, data quality checks, lineage jobs, API integrations, and AI-ready data products.
- Provide architecture support, stakeholder collaboration, and technical documentation across semantic architecture, data engineering, governance, and AI teams.
Desired Qualifications
- Experience with Neo4j, Amazon Neptune, GraphDB, Microsoft Purview, Unity Catalog, Immuta, Power BI Semantic Models, GraphRAG, vector search, and enterprise AI solutions.
- Ability to operationalise semantic architecture into reusable pipelines, semantic models, metadata assets, and knowledge graph solutions.
- Ability to collaborate across semantic architects, data architects, data engineers, governance teams, stakeholders, and AI engineering teams.
- Experience building governed, lineage-aware, observable, and AI-ready semantic data products for enterprise search, GraphRAG, and self-service analytics.
- Ability to document implementation patterns, support architecture decisions, and improve operational reliability through DevOps, Data SRE, and observability practices.
About the company
EY (Ernst & Young) provides professional services at a global scale, offering consulting, assurance, tax, and transaction advisory services. It serves clients across industries such as technology, media, real estate, hospitality, and construction. Instead of selling a single product, EY works with clients through tailored engagements where cross-disciplinary teams analyze challenges, design strategies, perform audits, help with tax planning, and assist with mergers or divestitures. What sets EY apart is its worldwide reach and integrated service model, industry-specific expertise, and focus on responsible business practices like sustainability, cybersecurity, and workforce flexibility. EY’s goal is to help organizations improve performance, manage risk, and achieve sustainable growth while building a better working world.
Company Size
5,001-10,000
Company Stage
N/A
Total Funding
N/A
Headquarters
Boston, Massachusetts
Founded
1991
Get referred to Ernst & Young
See people who can refer or advise you
Simplify's Take
What believers are saying
- EY.ai Agentic for Sales launched March 2, 2026 with Snowflake and Canva.
- EY uses client-zero deployments, scaling Copilot across 400,000 people by May 2026.
- EY’s 2026 AI assurance push monetizes client demand for governance, controls, and risk reviews.
What critics are saying
- Sabah filed RM2.4 billion audit-negligence claims against EY on July 30, 2026.
- EY set aside £188 million in March 2026 after NMC, Shell, and Made.com scrutiny.
- Repeated audit failures can destroy trust, trigger client defections, and shrink the franchise permanently.
What makes Ernst & Young unique
- EY Canvas processes 1.4 trillion journal-entry lines across 160,000 global audits.
- EY-Microsoft invested US$1b+ in May 2026 to industrialize enterprise AI delivery.
- EY launched agentic audit AI on April 7, 2026, spanning Assurance and AI assurance.
Help us improve and share your feedback! Did you find this helpful?
Benefits
- Professional Development Budget
- Flexible Work Hours
- Remote Work Options