Back
Niche knowledge-graph skillset reduces supply, but metro locations and mid-level role drive moderate competition.
Core knowledge-graph and LLM skills are transferable, but TSF domain expertise limits cross-industry fit.
Multiple mandatory niche skills (RDF/OWL, SPARQL, LLM extraction, GraphRAG) make screening highly selective.
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 automated pipelines for extracting knowledge from unstructured and semi-structured technical mining and asset documents into RDF-based knowledge graphs.
Develop and manage domain ontologies and schemas using RDF/OWL to support structured storage and reasoning over mining-related data, ensuring alignment with industry and internal standards.
Build graph-native retrieval pipelines including GraphRAG architectures for natural-language querying and AI-assisted analytics over knowledge graphs.
Proven experience as a Knowledge Engineer, Ontology Engineer, or Knowledge Graph Engineer specified in the mining or asset management domain is preferred but not explicitly confined.
Strong understanding and hands-on experience with RDF, OWL, SPARQL, and semantic data modeling.
Experience with RDF-based graph repositories (e.g., GraphDB, RDFox, Apache Jena, Neptune) and designing automated extraction pipelines utilizing Large Language Models and vision-based processing (OCR, layout analysis).
Work Experience Required: Not explicitly mentioned in the JD. Background verification completion is mandatory.
Experienced in building knowledge extraction and ingestion workflows combining LLM and vision-based AI techniques for complex technical document types.
Skilled in ontology design and management with semantic web standards to support structured risk, TSF, and asset-related knowledge graphs.
Capable of developing graph-native retrieval and reasoning systems, including GraphRAG, to enhance search and AI interaction over knowledge graphs in cloud environments like Azure.