Data & AI Strategy Knowledge Graph Engineer, hibrido
Empresa
Accenture
Provincia
Madrid
Ciudad
Madrid
Tipo de Contrato
Tiempo Completo
Descripción
Data & AI Strategy Knowledge Graph Engineer
Are you ready to design the semantic backbone of next-generation AI systems? At Accenture, we are reinventing organizations through technology, data, and artificial intelligence-helping clients unlock new sources of value and measurable impact for their businesses and society.
We are looking for a Knowledge Graph Engineer - Agentic AI to join our global team. This role focuses on the design and implementation of enterprise Knowledge Graphs that power advanced AI systems, combining deep technical expertise in semantic modeling with the integration of Agentic AI architectures.
You will play a key role in building graph-based foundations that enable explainable, context-aware, and scalable AI solutions. From defining ontologies and entity resolution strategies to enabling advanced retrieval patterns for AI agents, you will contribute across the full technical lifecycle-design, development, integration, and deployment.
As part of our team, you will work on cutting-edge initiatives that go beyond connecting existing tools. You will help engineer robust semantic layers and graph-enabled AI platforms that support multi-agent orchestration, Retrieval-Augmented Generation (RAG), and LLM-based systems-ensuring they are grounded, reliable, and aligned with enterprise data strategies.
While the role is deeply technical, you will also collaborate with architects and strategists to ensure that semantic and AI solutions translate into measurable business outcomes.
Key Responsibilities
- Design, implement, and maintain enterprise Knowledge Graphs using RDF/OWL and/or property graph models, including ontology design and semantic data modeling.
- Define graph schemas and relationships aligned with enterprise data structures (IDs, keys, lineage), ensuring consistency across domains.
- Implement entity resolution mechanisms and master data harmonization strategies.
- Build and manage ingestion pipelines from structured data sources into the Knowledge Graph, including incremental updates and synchronization processes.
- Develop, optimize, and maintain SPARQL and/or Cypher queries to enable performant and scalable graph operations.
- Design and implement structured retrieval patterns to support LLM grounding, RAG pipelines, and multi-agent systems.
- Integrate Knowledge Graphs with vector databases, LLM-based systems, and orchestration frameworks.
- Ensure performance optimization, scalability, security, and maintainability of graph and AI-integrated architectures.
How does the ideal candidate look like:
- +3 years in Data AI projects (strategy and/or technical development), ideally with exposure to Supply Chain Operations or related domains.
- Hands-on technical experience in building AI solutions with: Programming (Python), Large Language Models (LLMs), Prompt engineering, Retrieval-Augmented Generation (RAG), Multi-agent orchestration and Knowledge graph design and integration
- Understanding of AI solution lifecycle, including architecture, deployment, and governance for scalable agentic AI systems.
- Experience integrating graph-based reasoning with AI/LLM systems.
- Business case development and KPI definition.
- Analytical and problem-solving mindset, capable of designing innovative solutions and ensuring reliability and security.
- Excellent communication and presentation skills, simplifying complexity for diverse audiences.
- Adaptability and collaboration in global, fast-paced, multidisciplinary environments.
- Proficiency in English (required) additional languages are a plus.
The position is based in Barcelona or Madrid and follows a hybrid work model, with some days working from home and others in the office, where you can create interesting synergies with the rest of your team. It is essential to reside in Spain and have a work permit in Spain.
Technical Skills (Core)
- Programming: Strong proficiency in Python experience working with APIs and integration frameworks.
- Knowledge Graphs:- RDF/OWL and/or property graph modeling
- Ontology design and semantic data modeling
- SPARQL and/or Cypher
- Entity resolution and master data harmonization
- Schema design aligned with enterprise data structures (IDs, keys, lineage)
- Graph ingestion and incremental update mechanisms
- AI Integration:- Large Language Models (LLMs)
- Retrieval-Augmented Generation (RAG)
- Multi-agent orchestration frameworks
- Vector databases and hybrid retrieval architectures
- Prompt engineering for structured grounding
- Data Architecture:- Data modeling and integration
- Data governance, quality, and lineage principles
- Scalable and secure AI/graph architectures
- Cloud Platforms: Azure AI, Copilot Studio, or similar AI/graph deployment environments.
- Security Compliance: Secure design and deployment of AI-enabled systems.
Soft Skills
- Critical Thinking Problem Solving: Structured approach to complex challenges.
- Communication Presentation: Simplifying technical complexity for diverse audiences.
- Adaptability: Thriving in global, fast-paced, and evolving environments.
- Data AI Strategy: Ability to define and execute strategies aligned with business objectives.
- Business Case Development: Quantifying impact, defining KPIs, and aligning with executive priorities.
Python, LLM, SPARQL
Are you ready to design the semantic backbone of next-generation AI systems? At Accenture, we are reinventing organizations through technology, data, and artificial intelligence-helping clients unlock new sources of value and measurable impact for their businesses and society.
We are looking for a Knowledge Graph Engineer - Agentic AI to join our global team. This role focuses on the design and implementation of enterprise Knowledge Graphs that power advanced AI systems, combining deep technical expertise in semantic modeling with the integration of Agentic AI architectures.
You will play a key role in building graph-based foundations that enable explainable, context-aware, and scalable AI solutions. From defining ontologies and entity resolution strategies to enabling advanced retrieval patterns for AI agents, you will contribute across the full technical lifecycle-design, development, integration, and deployment.
As part of our team, you will work on cutting-edge initiatives that go beyond connecting existing tools. You will help engineer robust semantic layers and graph-enabled AI platforms that support multi-agent orchestration, Retrieval-Augmented Generation (RAG), and LLM-based systems-ensuring they are grounded, reliable, and aligned with enterprise data strategies.
While the role is deeply technical, you will also collaborate with architects and strategists to ensure that semantic and AI solutions translate into measurable business outcomes.
Key Responsibilities
- Design, implement, and maintain enterprise Knowledge Graphs using RDF/OWL and/or property graph models, including ontology design and semantic data modeling.
- Define graph schemas and relationships aligned with enterprise data structures (IDs, keys, lineage), ensuring consistency across domains.
- Implement entity resolution mechanisms and master data harmonization strategies.
- Build and manage ingestion pipelines from structured data sources into the Knowledge Graph, including incremental updates and synchronization processes.
- Develop, optimize, and maintain SPARQL and/or Cypher queries to enable performant and scalable graph operations.
- Design and implement structured retrieval patterns to support LLM grounding, RAG pipelines, and multi-agent systems.
- Integrate Knowledge Graphs with vector databases, LLM-based systems, and orchestration frameworks.
- Ensure performance optimization, scalability, security, and maintainability of graph and AI-integrated architectures.
How does the ideal candidate look like:
- +3 years in Data AI projects (strategy and/or technical development), ideally with exposure to Supply Chain Operations or related domains.
- Hands-on technical experience in building AI solutions with: Programming (Python), Large Language Models (LLMs), Prompt engineering, Retrieval-Augmented Generation (RAG), Multi-agent orchestration and Knowledge graph design and integration
- Understanding of AI solution lifecycle, including architecture, deployment, and governance for scalable agentic AI systems.
- Experience integrating graph-based reasoning with AI/LLM systems.
- Business case development and KPI definition.
- Analytical and problem-solving mindset, capable of designing innovative solutions and ensuring reliability and security.
- Excellent communication and presentation skills, simplifying complexity for diverse audiences.
- Adaptability and collaboration in global, fast-paced, multidisciplinary environments.
- Proficiency in English (required) additional languages are a plus.
The position is based in Barcelona or Madrid and follows a hybrid work model, with some days working from home and others in the office, where you can create interesting synergies with the rest of your team. It is essential to reside in Spain and have a work permit in Spain.
Technical Skills (Core)
- Programming: Strong proficiency in Python experience working with APIs and integration frameworks.
- Knowledge Graphs:- RDF/OWL and/or property graph modeling
- Ontology design and semantic data modeling
- SPARQL and/or Cypher
- Entity resolution and master data harmonization
- Schema design aligned with enterprise data structures (IDs, keys, lineage)
- Graph ingestion and incremental update mechanisms
- AI Integration:- Large Language Models (LLMs)
- Retrieval-Augmented Generation (RAG)
- Multi-agent orchestration frameworks
- Vector databases and hybrid retrieval architectures
- Prompt engineering for structured grounding
- Data Architecture:- Data modeling and integration
- Data governance, quality, and lineage principles
- Scalable and secure AI/graph architectures
- Cloud Platforms: Azure AI, Copilot Studio, or similar AI/graph deployment environments.
- Security Compliance: Secure design and deployment of AI-enabled systems.
Soft Skills
- Critical Thinking Problem Solving: Structured approach to complex challenges.
- Communication Presentation: Simplifying technical complexity for diverse audiences.
- Adaptability: Thriving in global, fast-paced, and evolving environments.
- Data AI Strategy: Ability to define and execute strategies aligned with business objectives.
- Business Case Development: Quantifying impact, defining KPIs, and aligning with executive priorities.
Python, LLM, SPARQL