Senior Knowledge Graph Engineer - Ecovadis

OverviewAs Senior Knowledge Graph Engineer, you will operationalize domain ontologies into high-throughput graph systems powering autonomous AI agents for sustainability challenges.You’ll bridge unstructured disclosures and structured graphs, building scalable pipelines and entity resolution to create enterprise-ready data.You’ll collaborate across AI and data teams to enable real-time insights in decarbonisation, sustainable procurement, and supply chain resilience.This role offers hands-on impact at the AI Center of Excellence shaping how EcoVadis uses AI for global sustainability.Compensaciones / BeneficiosRemote work from SpainFlexible working hoursWellness allowanceMental health supportLearning and developmentPrivate Health InsuranceResponsabilidadesDesign, implement, and maintain high-speed GraphRAG ingestion pipelines for relational, unstructured, and streaming data into labeled property graphs and RDF storesDevelop automated NER, linking, and deduplication workflows to resolve vendor profiles, SKUs, and coordinates into canonical graph nodesEnable semantic federation by ETL/ELT pipelines to map internal data with external ontologies and registries (GLEIF, W3C SSN/SOSA, Copernicus, PROV-O)Collaborate to build low-latency GraphRAG retrieval layers, write optimized Cypher and SPARQL queries, and support NL2Query for agentsOperationalize SHACL shapes in CI/CD data quality tests to prevent non-compliant data mutationsOptimize multi-hop query performance, partitioning, and indexing for sub-second traversal over billions of nodes and edgesRequisitos principalesDegree in Computer Science, Mathematics, Engineering, or related technical discipline4+ years of production experience with graph databases (Neo4j, Memgraph, TigerGraph) or RDF stores (GraphDB, Stardog, Virtuoso)Strong cloud experience, preferably Azure ecosystemAdvanced Python (RDFLib, NetworkX, PyGraphistry)Experience with NLP frameworks for entity extraction (LangChain, LlamaIndex, spaCy) or LLM-based extractionExperience with dbt and integrating graphs with vector stores (Qdrant, Pinecone, pgvector) for hybrid searchSolid knowledge of semantic web standards (RDF, RDFS, OWL, SKOS, SHACL, SPARQL) and data modeling (RML, R2RML)Experience with domain-specific supply chain, carbon accounting (GHG Protocol), or lifecycle data is a plusExperience building MCP servers to expose graph tools to LLM agents is a plusExperience with enterprise OBDA approaches at scale is a plusCollaborative, cross-functional communicationStructured problem solvingAttention to data quality and reproducibilityNeo4j, Memgraph, TigerGraphGraphDB, Stardog, VirtuosoCypher, SPARQL

Requisitos principalesDegree in Computer Science, Mathematics, Engineering, or related technical discipline 4+ years of production experience with graph databases (Neo4j, Memgraph, TigerGraph) or RDF stores (GraphDB, Stardog, Virtuoso) Strong cloud experience, preferably Azure ecosystem Advanced Python (RDFLib, NetworkX, PyGraphistry) Experience with NLP frameworks for entity extraction (LangChain, LlamaIndex, spaCy) or LLM-based extraction Experience with dbt and integrating graphs with vector stores (Qdrant, Pinecone, pgvector) for hybrid search Solid knowledge of semantic web standards (RDF, RDFS, OWL, SKOS, SHACL, SPARQL) and data modeling (RML, R2RML) Experience with domain-specific supply chain, carbon accounting (GHG Protocol), or lifecycle data is a plus Experience building MCP servers to expose graph tools to LLM agents is a plus Experience with enterprise OBDA approaches at scale is a plus Collaborative, cross-functional communication Structured problem solving Attention to data quality and reproducibility Neo4j, Memgraph, TigerGraph GraphDB, Stardog, Virtuoso Cypher, SPARQL