Senior Knowledge Graph Engineer

About the role

EcoVadis, a provider of business sustainability ratings, is looking for a hands-on, production-focused Senior Knowledge Graph Engineer to join its growing AI Center of Excellence. The role takes formal domain ontologies designed by Knowledge Representation Architects and turns them into high-throughput, multi-hop systems that power autonomous AI agents solving sustainability challenges such as decarbonisation, sustainable procurement compliance and supply chain resilience. It bridges unstructured sustainability disclosures and structured graph databases, building entity-resolution pipelines that make enterprise data agent-ready.

Key responsibilities

• Design, implement and maintain high-speed GraphRAG ingestion pipelines that turn ERP, SQL, ESG reports and streaming feeds into Labeled Property Graphs (Neo4j, Memgraph) and RDF triple stores.
• Build automated NER, entity linking and deduplication workflows to unify vendor profiles, SKUs and facility coordinates into canonical graph nodes.
• Implement ETL/ELT pipelines that federate internal supply chain data with external ontologies and registries (GLEIF, W3C SSN/SOSA, Copernicus, PROV-O).
• Partner with AI/ML engineers on low-latency GraphRAG retrieval, Cypher and SPARQL queries, NL2Query tools, hybrid vector-graph indexing and Model Context Protocol (MCP) tool endpoints.
• Turn SHACL shapes into automated data quality tests in CI/CD pipelines.
• Optimize multi-hop query performance, graph partitioning and indexing for sub-second traversal over billions of nodes and edges.

Required profile

• Degree in Computer Science, Mathematics, Engineering or a related technical discipline.
• 4+ years of production experience building and querying graph databases, especially Labeled Property Graphs (Neo4j, Memgraph, TigerGraph) or RDF triple stores (GraphDB, Stardog, Virtuoso).
• Experience with entity extraction pipelines using LangChain, LlamaIndex, spaCy or LLM-based extraction.
• Experience with dbt and integrating graph databases with vector stores (Qdrant, Pinecone, pgvector) for hybrid search.
• Solid understanding of RDF, RDFS, OWL, SKOS, SHACL, SPARQL, T-Box/A-Box separation and mapping languages (RML, R2RML).
• Supply chain, GHG Protocol or LCA data experience is a plus; MCP server and enterprise OBDA experience are also a plus.

Required skills

• Cloud technology, preferably Azure (Azure Foundry, Bicep, AzureML, Azure Cloud Storage)
• Python (RDFLib, NetworkX, PyGraphistry)
• SPARQL, Cypher, SHACL, SPARQL

What we offer

• Hybrid in Barcelona (2 days per week in the office) or full remote from Spain, with office and IT equipment support.
• Flexible working hours, wellness allowance and access to mental health support.
• Learning and development, peer recognition, remote work from abroad, meals and transport vouchers, dental benefits and life and accident insurance.
• Summer hours in July and August (36 hours per week) and a hybrid monthly allowance for electricity and internet.