Senior Knowledge Graph Engineer

This is a fully remote position, open to applicants in Poland.

📋 Description

• Design, implement, and maintain high-speed GraphRAG ingestion pipelines that convert relational data, unstructured ESG reports, and streaming feeds into operational Labeled Property Graphs and RDF Triple Stores.

• Develop automated workflows for Named Entity Recognition, entity linking, and deduplication to create unified canonical graph nodes.

• Create automated ETL/ELT pipelines to integrate internal supply chain data with external ontologies and registries.

• Collaborate with AI/ML Engineers to establish low-latency GraphRAG retrieval layers, optimize Cypher and SPARQL queries, develop NL2Query tools, and create hybrid vector-graph indexing pipelines and MCP tool endpoints.

• Operationalize SHACL shapes as automated data-quality assessments within CI/CD pipelines.

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

• Enable autonomous AI agents to tackle decarbonization, sustainable procurement compliance, and supply chain resilience challenges.

• Connect unstructured sustainability disclosures with structured graph databases through entity-resolution pipelines.

⛳️ Requirements

• A degree in Computer Science, Mathematics, Engineering, or a related technical field.

• Over 4 years of production experience in building and querying graph databases, particularly Labeled Property Graphs (Neo4j, Memgraph, TigerGraph) or RDF Triple Stores (GraphDB, Stardog, Virtuoso).

• Extensive experience with cloud technologies, ideally within the Azure ecosystem (e.g., Azure Foundry, Azure Bicep, AzureML, and Azure Cloud Storage).

• Advanced skills in Python (RDFLib, NetworkX, PyGraphistry) for developing scalable, production-ready data pipelines.

• Experience in creating entity extraction pipelines utilizing modern NLP frameworks (LangChain, LlamaIndex, spaCy) or LLM-based structured extraction.

• Practical experience with contemporary data transformation tools (dbt) and the integration of graph databases with vector stores (Qdrant, Pinecone, pgvector) for hybrid search architectures.

• Strong knowledge of semantic web standards (RDF, RDFS, OWL, SKOS, SHACL, RDF-star, SPARQL), principles of graph schema design (T-Box vs. A-Box separation), and mapping languages (RML, R2RML).

• Familiarity with domain-specific data structures related to supply chain, carbon accounting (GHG Protocol), or lifecycle assessment (LCA) is advantageous.

• Direct experience in building Model Context Protocol (MCP) servers to enable graph tools for LLM agents is a plus.

• Experience with enterprise OBDA approaches at scale is a plus.

• Must be eligible to work and reside in Poland.

• CV must be submitted in English.

🏝️ Benefits

• Provision of all necessary office and IT equipment.

• Flexible working hours.

• Wellness allowance to support mental and physical health.

• Access to professional mental health services.

• Referral bonus program.

• Opportunities for learning and development.

• Participation in sustainability events and community outreach.

• Peer recognition initiatives.

• Employee-led resource groups.

• Optional fully covered or co-financed health care and life insurance.

• Multisport card.

• Multikafeteria.

• Lunch card.

• Hybrid work arrangement.

• Remote work policy for international locations.

• Internet and electricity bill allowances.

• An additional day off for community service while volunteering.