Knowledge Engineering Consultant

Who we are: Accenture Song Service helps leading brands turn customer interactions into an engine for growth, moving service beyond a cost center to something that builds trust, loyalty, and share of wallet. Our Service practice works end to end: we shape the vision and strategy for the service function and help clients implement and run it, innovate the products and services customers rely on, equip client customer service and customer experience teams with the right technology and talent, and turn customer data into insights that strengthen client’s relationship with their customers. Service AI & Data puts AI at the heart of this work. We help clients reinvent how they serve their customers and support their people: conversational AI and AI agents that resolve customer needs across voice, chat, and messaging; and copilots that help service agents and field teams do their best work. All of this frontline work is powered by a trusted knowledge base that provides the right information, processes, and systems for every interaction. We also build the data foundations, data lakes, reporting, and analytics agents that turn every interaction into insight. The strategies we shape and the experiences we design are delivered into production at enterprise scale. Who you are: You are a hands-on knowledge engineer growing into a team lead, well versed in the full knowledge graph development lifecycle. You turn the scattered knowledge behind customer service, such as knowledge articles, policies, product information, troubleshooting guides, and case history, into a single, trusted source of truth that AI agents, service agents, and customers can rely on. You formulate real-world service problems into practical, efficient, and scalable AI and knowledge graph solutions, working across the lifecycle from ingestion through modeling, curation, and deployment. You design, evaluate, and maintain ontologies, apply current methods with the right architecture, and stay current with knowledge engineering, generative AI, LLMs, and multimodal models, looking for ways to apply them to the problem at hand. You explain the value of knowledge graph and AI approaches in plain language, share what you learn with the team, and begin to guide junior engineers. You collaborate with business users, engineers, architects, and designers to deliver your part of an end-to-end solution. The work: • Assess a client's service knowledge landscape: where knowledge lives today across knowledge bases, document repositories, CRM and ticketing systems, and agent notes, and where it is duplicated, conflicting, or out of date. • Build knowledge graph components that consolidate service knowledge into one source of truth and contribute to transforming the client's data architecture. • Design and maintain service ontologies and taxonomies that model products, customer issues, symptoms, resolutions, policies, and entitlements, so knowledge can be found, connected, and reasoned over. • Build ingestion and curation pipelines that turn unstructured content, such as articles, manuals, policies, and interaction transcripts, into structured, governed knowledge. • Make the knowledge base the trusted input for AI, preparing and structuring knowledge for retrieval through knowledge graphs, GraphRAG, and vector search, so virtual agents, agent-assist copilots, and analytics agents give accurate, consistent, and current answers. You work closely with the AI Solution Engineering teams who build those agents. • Build governance into the knowledge itself, including ownership, versioning, review cycles, and access rules that separate customer-facing content from internal-only guidance. • Mine service interactions to find knowledge gaps, such as questions customers ask that neither AI nor service agents can answer well, and feed them back into content creation and curation. • Design, develop, and implement AI and semantic solutions, and make sure your work integrates cleanly with the broader system, working alongside Enterprise AI Architecture teams on connections to service platforms. • Build solid working relationships with client counterparts, including knowledge managers and service operations teams, and work alongside the project team and delivery leads. • Help assemble the supporting evidence for the recommended semantic layer solution, and support Accenture sales efforts when called on. • Keep developing your skills in cutting-edge Data & AI solutions, especially agentic technologies, and share what you learn with the team. Here's what you'll need: • 3+ years of experience working on customer service, contact center, or customer experience projects or operations, with an understanding of how knowledge quality affects service outcomes such as first-contact resolution, average handle time, containment, and CSAT. • At least 3 of the following: • Minimum 2 years of experience with knowledge graph technologies (RDF, SPARQL, LPG, SHACL). • Minimum 2 years of experience in schema design, ontology management, and knowledge graph curation. • Minimum 2 years of designing and developing knowledge graph solutions and graph-based ML models (functional and technical). • Minimum 1 year of experience with end-to-end data pipeline implementation for AI applications (especially LLMs), with hands-on design and configuration. • Minimum 2 years of experience with relational databases, object stores, graph databases (Stardog, Neo4j, Amazon Neptune), and vector databases. Bonus points if you have: • Experience with service knowledge management platforms such as Salesforce Knowledge, ServiceNow Knowledge Management, eGain, or Zendesk, or with content repositories such as SharePoint and Confluence. • Familiarity with Knowledge-Centered Service (KCS) or similar knowledge management practices. • Experience with GraphRAG or other knowledge-grounded retrieval for AI agents. • 2+ years of hands-on experience with cloud platforms (AWS, Azure, Google Cloud