Senior Knowledge Graph Engineer

EcoVadis

18h•Hybrid

About The Position

EcoVadis is seeking a hands-on, production-focused Senior Knowledge Graph Engineer for its AI Center of Excellence. The role operationalizes formal domain ontologies into high-throughput, multi-hop systems that power autonomous AI agents addressing sustainability challenges, including decarbonisation, sustainable procurement compliance, and supply chain resilience. The engineer will bridge unstructured sustainability disclosures and structured graph databases by building entity-resolution pipelines that make enterprise data agent-ready. The position encompasses graph infrastructure and ingestion, entity resolution, semantic federation and external data integration, GraphRAG retrieval and agent tooling, deterministic data-quality guardrails, and GraphOps performance optimization. The role works in partnership with AI/ML Engineers and uses graph technologies and standards to integrate internal and external data into reliable, scalable knowledge graph systems. The role is hybrid in Barcelona, with two office days per week, or fully remote from Spain. Applicants must be eligible to work and live in Spain.

Requirements

Degree in Computer Science, Mathematics, Engineering, or a related technical discipline.
At least 4 years of production experience building and querying graph databases, specifically Labeled Property Graphs such as Neo4j, Memgraph, or TigerGraph, or RDF Triple Stores such as GraphDB, Stardog, or Virtuoso.
Strong experience with cloud technology, preferably Azure and its ecosystem, such as Azure Foundry, Azure Bicep, AzureML, and Azure Cloud Storage.
Advanced proficiency in Python, including RDFLib, NetworkX, or PyGraphistry, for building scalable, production-grade data pipelines.
Experience building entity-extraction pipelines using modern NLP frameworks such as LangChain, LlamaIndex, or spaCy, or LLM-based structured extraction.
Hands-on experience with modern data transformation tools such as dbt and integrating graph databases with vector stores such as Qdrant, Pinecone, or pgvector for hybrid search architectures.
Solid understanding of semantic web standards (RDF, RDFS and OWL, SKOS, SHACL, RDF-star, and SPARQL), graph schema design principles (T-Box versus A-Box separation), and mapping languages for heterogeneous data structures (RML, R2RML).
Eligible to work and live in Spain.

Nice To Haves

Experience working with domain-specific supply chain, carbon accounting (GHG Protocol), or lifecycle assessment (LCA) data structures.
Direct experience building Model Context Protocol (MCP) servers to expose graph tools to LLM agents.
Experience with enterprise OBDA approaches at scale.

Responsibilities

Design, implement, and maintain high-speed GraphRAG ingestion pipelines that transform relational data, unstructured ESG reports, and streaming feeds into operational Labeled Property Graphs and RDF Triple Stores.
Build automated Named Entity Recognition, entity-linking, and deduplication workflows to resolve mismatched vendor profiles, material SKUs, and facility coordinates into unified canonical graph nodes.
Implement automated ETL/ELT pipelines to map and federate internal supply chain data with external open-source ontologies and registries, including GLEIF, W3C SSN/SOSA, Copernicus, and PROV-O.
Partner with AI/ML Engineers to build low-latency GraphRAG retrieval layers, including optimized Cypher and SPARQL queries, NL2Query tools, hybrid vector-graph indexing pipelines, and MCP tool endpoints for autonomous LLM agents.
Operationalize SHACL shapes as automated data-quality tests in CI/CD pipelines to prevent hallucinated or non-compliant data mutations from entering the enterprise knowledge graph.
Optimize multi-hop query performance, graph partitioning, and database indexing to support sub-second traversal over billions of nodes and edges.