AI/Data Engineer en España

Mastery of semantic standards: OWL, RDF, RDFS, SPARQL, SHACL (at least one of them)

Experience with graph databases: Neo4j (Cypher), Amazon Neptune (Gremlin / SPARQL), Azure Cosmos DB (at least one of them)

Knowledge of RAG (Retrieval-Augmented Generation) architectures and their integration with LLMs

Experience with agent orchestration frameworks: LangGraph, LangChain, or similar (at least one of them)

Ability to extract and transform knowledge from unstructured sources (NLP, document parsing, integration with tools such as IDMC or MicroStrategy)

Familiarity with cloud platforms: preferably AWS (Bedrock, Neptune, Athena, S3) or Azure (OpenAI Service, Cosmos DB)

Minimum experience: 6–8 years in Data Engineering, Data Architecture, or AI roles, with at least 2–3 years of specialization in Knowledge Graphs or applied ontologies.

From Grupo NS, we are looking for an expert Knowledge Engineer.

The profile will work on projects designing and building the structured knowledge layers that support conversational AI systems, autonomous agents, and enterprise semantic platforms.

The role combines rigor in knowledge modeling with a data architecture vision and the ability to integrate with generative AI systems. This is not a purely theoretical profile: end-to-end delivery capability is expected, from business domain analysis to implementation and validation in production.

Main responsibilities

Design ontologies, taxonomies, and Knowledge Graphs that represent complex business domains (energy, operations, regulation)

Implement and maintain knowledge graphs using technologies such as Amazon Neptune, Neo4j, or Azure Cosmos DB

Develop knowledge extraction and structuring pipelines from heterogeneous sources (documents, ERP/SAP systems, APIs, relational databases)

Integrate semantic layers with RAG architectures and multi-agent systems based on LLMs (LangGraph, MCP, Bedrock)

Collaborate with Data Architecture, Data Engineering, and AI Engineering teams to ensure coherence between the operational data model and the knowledge model

Participate in the definition of the validation Golden Set and in the design of knowledge quality KPIs (hallucination rate, coverage, resolution rate)

Contribute to the standardization of methodologies and reusable assets within the capability