Role: Knowledge Graph (Full stack Engineer)Location: Barcelona, SpainMandatory skills: Exp. in delivering Semantic Knowledge Graph skills incl. AWS Neptune + Integrations Performance and use of MCP + Mulesoft API's + SLM & LLM fine tuning.The Full Stack Engineer is responsible for designing, building, and maintaining scalable data pipelines, knowledge graph, APIs, MCP endpoins for agentic AI, vector databases and RAG architecture based end-end platform that enable the delivery of high-quality data products for business and analytics use cases. This role focuses on transforming raw data into reliable, well-governed, and reusable assets that support agentic AI, insights generation, and machine learning use cases.The successful candidate works closely with product managers, data scientists, ontologists, architects, and business stakeholders to understand requirements and translate them into robust technical solutions. They develop and optimize data ingestion & transformation, knowledge graph engineering and enabling agentic AI usage across modern cloud and enterprise data environments, while ensuring strong standards for data quality, security, metadata, and compliance.The role also contributes to the full lifecycle of data products, from design and engineering through deployment, monitoring, and continuous improvement. A strong emphasis is placed on automation, scalability, observability, and maintainability, as well as enabling trusted and accessible data for end users. The Full Stack Engineer should combine solid software engineering practices (e.g. SOLID, DDD, Vibe Coding) with data management expertise and a delivery mindset focused on creating business value through dependable data products, delivered using an Agile frameworkTypical AccountabilitiesIdentify required source data:



Determine the necessary data sets, tables, and attributes from source systems needed to support the delivery of data products.Build and maintain ingestion integrations: Develop API-based integrations to receive and ingest data into Snowflake, using dbt for initial development and Fivetran for production deployment.Transform and integrate data: Perform required data transformations, standardisation, conformance, and joins across multiple data sets to deliver high-quality, reusable data products.Embed security and privacy controls: Ensure information security classification, data security, and data privacy requirements are maintained throughout the full lifecycle of each data set and its transformation into a data product, including the application of appropriate access controls, roles, and privileges.Enable data product connectivity: Create MCPs and APIs to support integration with and consumption of data products.Productionise data products: Support the implementation, operationalisation, and governance of data products, including documentation and registration within Collibra and Immuta.Document data assets and relationships: Maintain clear documentation for data products, underlying tables, attributes, and relationships between data sets to support transparency, lineage, and reuse.Optimise ingestion performance: Monitor and tune the performance of ingestion APIs and pipelines across Snowflake, dbt,



and Fivetran.Optimise integration performance for AI use cases: Tune the performance of MCPs and APIs used to integrate data products with SLMs and LLMs, including platforms such as Anthropic and MuleSoft.Build Semantic Knowledge Graph: Use the Semantic Data Products to build ontologies, vocabularies and Knowledge Graph in AWS Neptune as the foundations for RAG architecture. Enable AI agents to traverse the graph for autonomous execution.Education, Qualifications, and ExperienceBachelors Degree in Computer Science, Data Management or STEM subject5 - 10 year’s experience in industry data management, business analysis, data engineeringProblem SolvingProven delivery of Data Products, APIs and SLMs / LLMsProven delivery of RAG architectures using knowledge graphs, vector databases for agentic AI use caseProven experience of building MCP endpoints and tools for agentic AI use caseExperience in managing ontologies and controlled vocabularies for complex knowledge graphsMasters in Computer Science and Data Management or suitable experienceSkills and CapabilitiesSnowflake, dbt, SQL, security policies & roles, and APIsPython, ReactAWS (infrastructure as code, Quick, Connect, Security Agent, DevOps Agent, Bedrock, Nova)Knowledge Graphs – AWS Neptune, RDF, SPARQLFine tuning Small Language Models (SLMs)Mulesoft APIFiveTran API and custom API creationAnthropic MCP, concurrent Workstreams and performance tuning Microsoft CoPilot Studio, Agent buildeDemonstrate initiative, strong customer orientation, and cross-cultural workingAbility to influence senior leadership on plans, data risks and approachesStrong documentation of code and deliverablesAbility to take ownership and deliver within tight timescales
#J-18808-Ljbffr

📌 Full Stack Engineer (Barcelona)
🏢 Virtusa
📍 Barcelona