Knowledge Graph Engineer - Immediate joiners only & F2F interview is Mandatory

About the Role

We are looking for a Knowledge Graph Engineer to design, build, and scale an enterprise knowledge graph that powers semantic search, intelligent applications, analytics, and GenAI/LLM use cases. You will translate business entities, relationships, and domain knowledge into production-grade graph models and APIs.

Key Responsibilities

• Design and implement scalable knowledge graph schemas using property graph and/or RDF-based models.
• Develop and optimize graph queries using Cypher, SPARQL, or Gremlin.
• Build ingestion pipelines to transform structured, semi-structured, and unstructured enterprise data into graph structures.
• Create and maintain ontologies, taxonomies, semantic models, and canonical entity definitions.
• Implement entity resolution, deduplication, metadata enrichment, and relationship extraction.
• Define data-quality, validation, provenance, versioning, and governance standards for the knowledge graph.
• Build graph APIs and semantic access layers for downstream applications, search, analytics, and AI services.
• Optimize graph query performance, indexing, traversal efficiency, scalability, and security.
• Partner with data engineering, AI/ML, product, architecture, and domain teams to enable knowledge-driven workflows.
• Support LLM grounding, semantic retrieval, RAG pipelines, and hybrid search using graph and vector-based approaches.

Required Skills

• Bachelor's or Master's degree in Computer Science, Data Science, Engineering, Information Systems, or a related field.
• 5–8 years of experience in knowledge graph engineering, graph databases, semantic modeling, ontology engineering, or data architecture.
• Hands-on experience with at least one graph platform: Neo4j, AWS Neptune, Stardog, TigerGraph, GraphDB, or similar.
• Strong proficiency in Cypher, SPARQL, or Gremlin.
• Solid understanding of RDF, OWL, RDFS, SHACL, ontologies, taxonomies, and semantic web standards.
• Strong programming skills in Python; Java is a plus.
• Experience with data pipelines, ETL/ELT, APIs, SQL, and cloud-based data platforms.
• Experience with entity resolution, data quality, metadata management, and data governance.
• Strong communication skills and ability to translate business requirements into semantic/graph models.

Preferred Skills

• Experience integrating knowledge graphs with LLMs, RAG, embeddings, vector databases, and hybrid retrieval.
• Familiarity with cloud platforms such as AWS, Azure, or GCP and services such as Neptune, Databricks, BigQuery, Glue, or Vertex AI.
• Experience with Protégé, ontology modeling tools, and schema evolution.
• Exposure to graph machine learning or Graph Neural Networks (GNNs) using PyTorch Geometric or DGL.
• Experience in BFSI, healthcare, manufacturing, or other complex enterprise data domains is a plus.

What Success Looks Like

Within the first 6 months, you will have delivered a scalable knowledge graph foundation, established ontology and data-quality standards, enabled semantic search or AI-assisted retrieval use cases, and built reusable ingestion and graph-access components for enterprise teams.