Senior Knowledge Graph Engineer

EcoVadis is the leading provider of business sustainability ratings. Their solutions are backed by an international team of experts and powerful technology. They analyze data and build sustainability scorecards that give companies actionable insights into their environmental, social and ethical risks.

• Degree in Computer Science, Mathematics, Engineering, or related technical discipline.
• 4+ years production experience with graph databases, specifically Labeled Property Graphs (Neo4j, Memgraph, TigerGraph) or RDF Triple Stores (GraphDB, Stardog, Virtuoso).
• Strong experience with cloud technologies, preferably Azure (Azure Foundry, Azure Bicep, AzureML, Azure Cloud Storage).
• Advanced proficiency in Python (RDFLib, NetworkX, PyGraphistry) for scalable data pipelines.
• Experience building entity extraction pipelines using NLP frameworks (LangChain, LlamaIndex, spaCy) or LLM-based extraction.
• Hands-on experience with data transformation tools (dbt) and integrating graph databases with vector stores (Qdrant, Pinecone, pgvector).
• Solid understanding of semantic web standards (RDF, RDFS, OWL, SKOS, SHACL, RDF-star, SPARQL), graph schema design (T-Box vs. A-Box), and mapping languages (RML, R2RML).

Nice to have:

• Experience with supply chain, carbon accounting (GHG Protocol), or lifecycle assessment (LCA) data.
• Experience building Model Context Protocol (MCP) servers for LLM agents.
• Experience with enterprise OBDA approaches at scale.

Graph Infrastructure and Ingestion Pipelines:

• Design, implement, and maintain high-speed GraphRAG ingestion pipelines that transform relational data (ERP, SQL), unstructured ESG reports, and streaming feeds into operational Labeled Property Graphs (Neo4j, Memgraph) and RDF Triple Stores.

A-Box Instantiation and Entity Resolution:

• Build automated Named Entity Recognition (NER), entity linking, and deduplication workflows for unifying vendor profiles, material SKUs, and facility coordinates into canonical graph nodes.

Semantic Federation and External Data Integration:

• Implement automated ETL/ELT pipelines to map and federate supply chain data with external ontologies and registries (e.g., GLEIF, W3C SSN/SOSA, Copernicus, PROV-O).

GraphRAG and Agent Tooling:

• Collaborate with AI/ML Engineers to develop low-latency retrieval layers with optimized Cypher and SPARQL queries, NL2Query tools, hybrid vector-graph indexing, and Model Context Protocol (MCP) endpoints.

Deterministic Guardrails and Pipeline Validation:

• Operationalize SHACL (Shapes Constraint Language) into automated data quality tests within CI/CD pipelines to prevent non-compliant data mutations.

Performance Optimization and GraphOps:

• Optimize multi-hop query performance, graph partitioning, and indexing for sub-second traversal over billions of nodes and edges.

Offer available only for candidates eligible to work and live in Poland. Location: Hybrid in Warsaw (4 days per month in the office) / Full remote from Poland. EcoVadis commits to equity, inclusion, and reducing bias in hiring; applications from disabled, neurodiverse candidates, and those requiring adjustments are welcomed.