Capgemini - Principal Data Architect - AI Knowledge Platform

About the Company : We are seeking a Principal Knowledge & Data Platform Lead to architect the knowledge, retrieval, and context foundation that enables AI agents to reason, retrieve, learn, and operate safely in highly regulated environments. About the Role : This is a high-impact individual contributor role for a senior technologist who combines deep expertise in Knowledge Graphs, RAG, Context Engineering, AI Knowledge Management, and Enterprise Data Platforms. Responsibilities : - Enterprise Knowledge Graph architecture, ontology design, semantic modeling, and graph-based retrieval. - End-to-end RAG optimization including embeddings, hybrid search, GraphRAG, reranking, retrieval evaluation, and grounding quality. - Context Engineering frameworks that determine what information enters an agent's context window, when, and at what cost. - AI Knowledge Management lifecycle covering curation, provenance, versioning, freshness, governance, and auditability. - Agent Memory platforms supporting episodic and long-term memory across AI systems. - Permission-aware retrieval with tenant isolation, document-level security, compliance controls, and audit trails. - Data flywheel architecture transforming production data into training and evaluation assets for future LLM and SLM development. Preferred Skills : - Deep expertise in Neo4j, Knowledge Graphs, Ontologies, and Semantic Data Modeling. - Proven experience building and scaling production-grade RAG systems. - Strong understanding of GraphRAG, Hybrid Retrieval, Embedding Strategies, and Retrieval Evaluation. - Experience with Context Engineering, Agent Memory, and Agentic AI architectures. - Knowledge management expertise focused on AI consumption rather than traditional enterprise search. - Experience working within regulated industries such as Financial Services, Banking, Insurance, Healthcare, or GDPR-governed environments. - Technical leadership ability to define standards, influence architecture decisions, and drive adoption across multiple engineering teams. - GraphRAG, LangGraph, LangChain, MCP (Model Context Protocol). - Vector Databases, Enterprise Search, AI Observability. - LLM Evaluation Frameworks. - AI Platform Engineering & Agentic AI Systems. - Financial Services, Payments, Insurance, or Healthcare Domain Experience.