AI Context Architect

KPMG is currently seeking an AI Context Architect to join our Technology Organization (ATO).

• Lead the design of context architecture for KPMG Clara and the global content systems that feed our KPMG Clara AI solutions, defining how audit methodology, standards, engagement content and more are modeled, structured, and made machine-consumable
• Collaborate closely with AI engineers, content owners, and product managers to translate knowledge modeling and retrieval research into scalable, production-ready grounding components
• Design and champion a rigorous experimentation and evaluation framework to measure retrieval quality, grounding accuracy, and the reliability of AI-driven outcomes
• Drive the context and content strategy agenda by identifying emerging trends in knowledge representation and generative AI, proposing innovative solutions, and mentoring junior team members to foster a culture of continuous learning and excellence
• Design and implement processes across the content-to-context lifecycle; from content ingestion, structuring, and metadata enrichment, to chunking, indexing, and embedding strategies; work to ensure retrieval pipelines can be deployed and managed in production
• Architect and prototype novel context and retrieval approaches; share findings with colleagues across KPMG globally to advance wider AI and content modernization initiatives
• Act with integrity, professionalism, and personal responsibility to uphold KPMG's respectful and courteous work environment

• Minimum eight years of recent experience in applied AI/ML, information architecture, or knowledge engineering, with a focus on natural language processing, information retrieval, and large-scale language models
• Advanced degree (Ph.D. or Master's) from an accredited college or university is preferred; minimum of a Bachelor’s degree from an accredited college/university in computer science, AI, statistics, or a related quantitative field is required
• Deep theoretical knowledge and practical expertise in knowledge and content modeling (taxonomy, ontology, metadata, and structured content design) and in knowledge retrieval (RAG), including chunking, embedding, and grounding techniques for large language models
• Proven experience designing and implementing the end-to-end lifecycle for content and context pipelines, including content ingestion, structuring, enrichment, indexing, and production deployment
• Experience modeling information architecture systems into context architecture for use in AI solutions; extensive hands-on experience prototyping and experimenting with modern AI and retrieval frameworks, along with vector and search technologies
• Exceptional ability to translate ambiguous business and content challenges into defined architecture problems and articulate complex findings and their strategic implications to both technical and executive audiences(200
  
  TEC)