Senior Knowledge Graph Engineer

Hace 6 días

Barcelona, Cataluña, España EcoVadis Jornada completa
Overview

In this role you will operationalize domain ontologies into high-throughput graph systems powering autonomous AI agents solving sustainability challenges. You’ll bridge unstructured disclosures with structured graphs and build scalable ingestion and entity-resolution pipelines. You’ll enable semantic federation with external data and optimize performance for sub-second traversals at scale. You work closely with AI/ML engineers to drive practical, data-driven sustainability solutions.

Compensaciones / Beneficios
  • Flexible working hours
  • Wellness allowance
  • Mental health support
  • Remote work from abroad policy
  • Dental Benefits
  • Life & Accident Insurance + Private Health Insurance
Responsabilidades
  • Design and maintain high-speed GraphRAG ingestion pipelines converting ERP, SQL, unstructured ESG reports, and streaming data into labeled property graphs and RDF stores
  • Build automated NER, entity linking, and deduplication workflows to unify vendor profiles, SKUs, and coordinates into canonical graph nodes
  • Implement automated ETL/ELT pipelines to federate internal supply chain data with external ontologies and registries (GLEIF, W3C SSN/SOSA, Copernicus, PROV-O)
  • Develop low-latency GraphRAG retrieval layers, write Cypher and SPARQL queries, and create NL2Query tools for autonomous LLM agents
  • Operationalize SHACL shapes into automated data quality tests in CI/CD to prevent data mutations in the graph
  • Optimize multi-hop queries, graph partitioning, and indexing for sub-second traversal over billions of nodes and edges
  • Collaborate with AI/ML engineers to integrate graph databases with vector stores for hybrid search architectures
  • Ensure alignment with enterprise OBDA approaches and scalable graph tooling
Requisitos principales
  • Degree in Computer Science, Mathematics, Engineering, or a related technical discipline
  • 4+ years of production experience with graph databases (Neo4j, Memgraph, TigerGraph) or RDF stores (GraphDB, Stardog, Virtuoso)
  • Strong cloud experience (Azure preferred) and related tooling
  • Advanced Python skills (RDFLib, NetworkX, PyGraphistry) for scalable data pipelines
  • Experience with NLP frameworks (LangChain, LlamaIndex, spaCy) or LLM-based extraction
  • Hands-on with data transformation tools (dbt) and vector stores (Qdrant, Pinecone, pgvector) for hybrid search
  • Solid understanding of semantic web standards (RDF, RDFS, OWL, SKOS, SHACL, RDF-star, SPARQL) and mapping (RML, R2RML)
  • Experience with domain data in supply chain, carbon accounting (GHG Protocol), or LCA is a plus
  • Experience building MCP servers to expose graph tools to LLMs is a plus
  • Experience with enterprise OBDA approaches at scale is a plus
  • Collaborative
  • Problem-solving
  • Detail-oriented
  • Graph databases (Neo4j, Memgraph, TigerGraph)
  • RDF and SPARQL
  • Cypher