Back
Niche knowledge-graph specialization reduces candidate pool, but metro locations and known employer increase competition.
Role requires TSF domain ontology and asset expertise, making cross-industry transferability limited.
Many mandatory niche technical requirements (RDF/OWL, SPARQL, GraphRAG, LLMs, Azure) raise filter strictness.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Design and implement end-to-end knowledge extraction pipelines that transform unstructured/semi-structured technical documents into RDF-based knowledge graphs.
Develop and manage RDF/OWL ontologies and knowledge schemas for mining-related data, ensuring alignment with industry standards and internal models.
Build and maintain graph-native retrieval and reasoning workflows (GraphRAG) enabling natural-language querying and AI assistant support.
Proven experience as Knowledge Engineer or similar role focusing on ontology/knowledge graph engineering.
Strong expertise in RDF, OWL, SPARQL, and semantic data modeling with hands-on experience in graph repositories like GraphDB, RDFox, Neptune, or equivalent.
Experience designing and implementing automated knowledge extraction pipelines using LLMs and vision-based document processing (OCR, layout analysis).
Familiarity with Azure AI/data platforms and implementing hybrid GraphRAG architectures. Work Experience Required: Not explicitly mentioned in the JD. Notice Period: Not explicitly mentioned in the JD.
Technically skilled in AI-driven knowledge extraction combining LLM and vision modalities applied to complex, domain-specific technical documents.
Experienced in building and evolving domain-specific ontologies and scalable RDF-based knowledge graph infrastructures.
Comfortable working at the intersection of knowledge engineering, graph analytics, and large language model integration within cloud AI ecosystems.