AI Data Platform Engineer Knowledge Bases Graph GenAI

Title: Data Scientist / AI Data Platform Engineer Location: Madrid, Spain Work Mode: Hybrid-2-day a week Employment type: Permanent Job description AI Data Platform Engineer Knowledge Bases Graph GenAI We are looking for strong technical profiles to join a strategic initiative focused on building enterprise knowledge bases, knowledge graphs, semantic layers and AI-powered data access capabilities in a regulated banking environment. The role is hands-on and product-oriented with responsibility across design, development, integration and industrialisation of reusable components for structured and unstructured data exploitation Key responsibilities Design and implement knowledgebase creation and maintenance pipelines including semantic layer generation data graph creation and vector database pipelines Develop services and components for knowledgebase exposure and consumption including APIs assistant style interfaces and AI LLM based retrieval capabilities Integrate structured and unstructured enterprise repositories such as lake platforms S3file storage SharePoint FileNet and similar sources Build and evolve RAG semantic search metadata enrichment and natural language to data capabilities including Text to SQL where relevant Contribute to humanin the loop workflows quality controls monitoring observability and production readiness of the platform Work closely with technical leads architects data teams and business stakeholders in agile delivery squads Required experience and skills Strong Handson experience in Python and solid SQL skills Proven experience in software engineering data engineering or AI engineering in production environments Handson experience with graph databases including data modeling and query development using Gremlin SPARQL andor Cypher Strong experience designing and building RESTful APIs using FastAPI or similar frameworks including async patterns and performance optimization Practical experience integrating and consuming LLM services in cloud environments especially AWS Bedrock or similar platforms Solid experience with relational databases such as PostgreSQL and cloudnative variants like Amazon Aurora including schema design and performance tuning Experience building data access layers combining SQL graph queries and vector search Practical knowledge of Docker Gitbased workflows and CICD practices Experience working with cloud platforms Azure and AWS with deep experience in at least one AWS strongly preferred Strong understanding of scalability reliability security and maintainability considerations in enterprise systems Skills : GenAI - LLMOps, PostgreSQL