Semantic AI/ML Engineer-Web Ontology Language (Immediate joiner with short NP within 30 days)
Job Description
This includes collaborating with domain experts to capture real-world concepts and validate that the ontology accurately represents business knowledge.\n• Knowledge Graph Development: Build and manage enterprise knowledge graphs based on the defined ontologies, linking diverse data sources into a unified graph data model. This involves configuring graph databases or triple stores, populating the knowledge graph with data (RDF triples), and optimizing it for query performance and scalability.\n• Semantic Querying (SPARQL): Create and optimize SPARQL queries to enable efficient retrieval, integration, and analysis of data from the knowledge graph. You will develop semantic queries and endpoints that support advanced search and analytics use cases, making it easier for others to retrieve insights from linked data.\n• Integration with AI Agents: Work with AI agents and large language model (LLM) teams to leverage the ontology and knowledge graph for intelligent applications.
For instance, you might enable an AI chatbot to use the knowledge graph for more context-aware responses, or develop mechanisms for AI systems to perform reasoning over the ontologies. This responsibility ensures that semantic data structures enhance AI initiatives (e.g. improving context, disambiguation, and knowledge retrieval in AI workflows).\n\nMandatory Skills Description:\nOntology Design & Maintenance: Design, develop, and maintain ontologies (using OWL/RDF or similar).\n\nSemantic Web Proficiency: Strong knowledge of semantic web technologies and standards - specifically, hands-on proficiency with OWL (Web Ontology Language) and RDF (Resource Description Framework) for ontology modelling, as well as SPARQL for querying graph data.\n\nKnowledge Graph Experience: Practical experience building or maintaining knowledge graphs or linked data systems in an enterprise setting.\n\nData Modelling & Integration Skills: A solid understanding of data modelling principles, data architecture, and integrating heterogeneous data sources.
You should be capable of abstracting real-world entities into a semantic schema and mapping relational or NoSQL data to an ontology.\n\nProgramming Skills: Proficiency in at least one programming or scripting language (such as Python, Java, or similar)