> Markdown version of [/jobs/ext/2387455-solutions-architect](https://www.wearedevelopers.com/jobs/ext/2387455-solutions-architect). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Solutions Architect - **Company:** Capgemini - **Location:** London, UK (Remote available) - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Amazon Web Services, Automated Storage and Retrieval Systems, Audit Trail, Automation of Tests, Microsoft Azure, Cloud Engineering, Computer Programming, Continuous Integration, Information Engineering, Extract Transform Load (ETL), Distributed Computing Environment, Elasticsearch, Graph Database, Python (Programming Language), Knowledge Management, Meta-Data Management, Neo4j, Role-Based Access Control, Search Technologies, Management of Software Versions, Large Language Models, Multi-Agent Systems, Generative AI, Kubernetes, Data Lineage, Optimization Algorithms, Integration Frameworks, Machine Learning Operations, Virtual Agents, Data Pipelines, Docker - **Published:** August 6, 2026 - **Apply:** https://uk.indeed.com/viewjob?jk=ba33b7a93574c11d ## About the Role * Expertise in designing and implementing enterprise knowledge graphs, ontologies, and semantic data models. * Strong experience in Retrieval-Augmented Generation (RAG), GraphRAG, hybrid search, and semantic retrieval architectures. * Proficiency in vector databases, embedding technologies, reranking models, and retrieval optimization techniques. * Extensive knowledge of context engineering, prompt orchestration, and token budget optimization for AI agents. * Experience building and managing AI knowledge management platforms with strong governance and audit capabilities. * Strong understanding of agentic AI architectures, multi-agent systems, and long-term memory frameworks. * Expertise in metadata management, data lineage, provenance tracking, and knowledge lifecycle governance. * Hands-on experience with graph databases such as Neo4j, Amazon Neptune, TigerGraph, and ArangoDB. * Proficiency in Azure AI Search, Elasticsearch, Pinecone, Weaviate, Qdrant, and related retrieval technologies. * Strong programming and data engineering skills using Python and modern data processing frameworks. * Experience building scalable ETL/ELT pipelines and distributed data processing solutions. * Knowledge of LLMOps, MLOps, AI evaluation frameworks, and model fine-tuning techniques. * Expertise in implementing RBAC, ABAC, multi-tenant security models, and identity-aware retrieval systems. * Strong understanding of compliance, data privacy, auditability, and governance requirements in regulated industries. * Experience with cloud-native architectures using Azure, AWS, Kubernetes, Docker, and CI/CD pipelines. * Proven ability to lead platform strategy, enterprise architecture initiatives, and cross-functional engineering teams. * Excellent stakeholder management, communication, and technology leadership skills. ## Description Knowledge & Data Platform Lead (Principal) graph engineering, RAG optimisation, context engineering, and knowledge management for AI systems. Hybrid working: The places that you work from day to day will vary according to your role, your needs, and those of the business; it will be a blend of Company offices, client sites, and your home; noting that you will be unable to work at home 100% of the time. Your Role * Led the design and implementation of an enterprise knowledge platform that enabled AI agents across Insurance, Payments, and Healthcare domains. * Owned the architecture and governance of enterprise knowledge graphs, including ontology design, semantic modeling, and graph-based retrieval capabilities. * Developed and optimized end-to-end RAG and Graph RAG solutions to improve response accuracy, grounding, and contextual relevance. * Established context engineering standards by defining how knowledge, instructions, and business rules are selected and structured within AI agent contexts. * Managed the complete AI knowledge lifecycle, including ingestion, curation, versioning, provenance tracking, freshness monitoring, and deprecation of knowledge assets. * Designed and governed agent memory frameworks to support episodic, semantic, and precedent-based knowledge retrieval. * Implemented permission-aware retrieval systems with document-level security, identity propagation, multi-tenant isolation, and comprehensive audit trails. * Built evaluation frameworks and automated testing pipelines to measure retrieval effectiveness, grounding quality, relevance, and knowledge freshness. * Created data flywheel processes that transformed operational and domain data into high-quality training and evaluation datasets for AI models. * Collaborated with product, engineering, security, and governance teams to deliver scalable, compliant, and trustworthy AI solutions. * Defined platform standards, reusable architectures, and best practices adopted across multiple AI-powered product lines. Ensured compliance with regulatory, privacy, and security requirements within highly regulated financial and healthcare environments. * ## Related Videos - [Scaling GraphRAG: Efficient Knowledge Retrieval for AI](https://www.wearedevelopers.com/videos/100025-scaling-graphrag-efficient-knowledge-retrieval-for-ai) - [Putting the Graph In GraphQL With The Neo4j GraphQL Library](https://www.wearedevelopers.com/videos/257-putting-the-graph-in-graphql-with-the-neo4j-graphql-library) - [Docker Compose: Rediscovered](https://www.wearedevelopers.com/videos/1978-docker-compose-rediscovered) - [Understanding Kubernetes in a visual way](https://www.wearedevelopers.com/videos/100085-understanding-kubernetes-in-a-visual-way) - [Graphs and RAGs Everywhere... But What Are They? - Andreas Kollegger - Neo4j](https://www.wearedevelopers.com/videos/1311-graphs-and-rags-everywhere-but-what-are-they-andreas-kollegger-neo4j) - [Microservices: how to get started with Spring Boot and Kubernetes](https://www.wearedevelopers.com/videos/242-microservices-how-to-get-started-with-spring-boot-and-kubernetes) ## Related Articles - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering) - [Everything a Developer Needs to Know About MCP with Neo4j](https://www.wearedevelopers.com/magazine/604-everything-a-developer-needs-to-know-about-mcp-with-neo4j) - [Coffee with Developers - Maria Apazoglou - Making AI understandable for all in production](https://www.wearedevelopers.com/magazine/475-coffee-with-developers-maria-apazoglou-making-ai-understandable-for-all-in-production) - [Got AI ideas but no money? Here are 10 free ways to level up your AI skills with Google Cloud](https://www.wearedevelopers.com/magazine/600-got-ai-ideas-but-no-money-here-are-10-free-ways-to-level-up-your-ai-skills-with-google-cloud) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care)