\\\\Introduction\\\\ A career in IBM Consulting is built on long-term client relationships and close collaboration worldwide. Youll work with leading companies across industries, helping them shape their hybrid cloud and AI journeys. With support from our strategic partners, robust IBM technology, and Red Hat, youll have the tools to drive meaningful change and accelerate client impact. At IBM Consulting, curiosity fuels success. Youll be encouraged to challenge the norm, explore new ideas, and create innovative solutions that deliver real results. Our culture of growth and empathy focuses on your long-term career development while valuing your unique skills and experiences. \\\\Your role and responsibilities\\\\ Responsible for designing the semantic knowledge layer making the clients news vector store AI ready. Defines how unstructured news data, structured metadata, and formal ontologies are integrated into a coherent semantic model suitable for vector search and AI-driven analytics. Hands on architect for owning the embedding strategy, chunking methodology, metadata alignment, and retrieval evaluation framework. Ensures that the vector database and MCP serving layer operate on a well-defined, consistent semantic foundation aligned with the clients analytical and policy use cases. \\\\Required technical and professional expertise\\\\ '- Proven experience designing and deploying production retrieval or RAG systems and strong expertise in embedding models and vector retrieval architectures. Experience selecting, benchmarking, and versioning embedding engines. \- Experience designing and implementing retrieval quality measurement frameworks. \- Experience integrating structured metadata into vector indexing and retrieval systems. \- Experience designing chunking and indexing strategies for long-form domain-specific text. \- Ability to define semantic governance processes (embedding lifecycle, ontology evolution, re-indexing strategy, document/query similarity calculation algorithms. Experience working with ontologies, controlled vocabularies, or semantic taxonomies. \- Experienced in Python or other coding language skills. \\\\Preferred technical and professional experience\\\\ '\- Experience integrating vector databases. \- Knowledge graph or entity-resolution experience. Experience working in regulated institutional environments. \- Experience mapping external ontologies into search/index schemas. Experience on solutions for improving sovereignty & portability. \- Experience with permission management in OpenSearch (including filtering of chunks/documents to which one does not have access) and integration with IdP. \- Knowledge about dimensionality reduction techniques (PCA, MRL and alike) \- Knowledge on embedding quantization to improve retrieval and indexing time as well as reduce compute costs. IBM is committed to creating a diverse environment and is proud to be an equal-opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, gender, gender identity or expression, sexual orientation, national origin, caste, genetics, pregnancy, disability, neurodivergence, age, veteran status, or other characteristics. IBM is also committed to compliance with all fair employment practices regarding citizenship and immigration status.

The role requires proven experience in designing and deploying production retrieval or RAG systems, with strong expertise in embedding models and vector retrieval architectures. This includes selecting, benchmarking, and versioning embedding engines. Experience in designing and implementing retrieval quality measurement frameworks is necessary. The candidate must be able to integrate structured metadata into vector indexing and retrieval systems, and design chunking and indexing strategies for long-form domain-specific text. Defining semantic governance processes, including embedding lifecycle, ontology evolution, re-indexing strategy, and document/query similarity calculation algorithms, is also required. Experience working with ontologies, controlled vocabularies, or semantic taxonomies is essential, along with proficiency in Python or other coding languages.