Overview In this role you will lead the design of context architecture for KPMG Clara and its global content systems, enabling machine-consumable knowledge models for AI solutions. You will collaborate with AI engineers, content owners, and product managers to translate research into scalable grounding components. You will establish an experimentation framework to evaluate retrieval quality and grounding reliability of AI-driven outcomes. You will drive content strategy, mentor junior teammates, and oversee end-to-end content-to-context processes for production-ready pipelines. This role offers high-impact work at scale within a culture of learning and excellence.
Compensation / Benefits- medical and dental plans
- vision coverage
- disability and life insurance
- 401(k) plans
- well-being benefits
- Personal Time Off
Responsibilities- Lead the design of context architecture for KPMG Clara and global content systems feeding Clara AI solutions
- Collaborate with AI engineers, content owners, and product managers to translate knowledge modeling into production-ready grounding components
- Design and champion an experimentation framework to measure retrieval quality and grounding accuracy
- Drive the content strategy by identifying trends in knowledge representation and mentoring junior team members
- Design and implement end-to-end content-to-context processes: ingestion, structuring, metadata enrichment, chunking, indexing, and embedding
- Prototype novel context and retrieval approaches and share findings across KPMG globally
- Uphold integrity and a respectful work environment
Key requirements- 8 years of experience in applied AI/ML, information architecture, or knowledge engineering with NLP, information retrieval, and large-scale language models
- Advanced degree preferred (Ph.D. or Master's); Bachelor in CS/AI/quantitative field required
- Deep knowledge of knowledge/content modeling (taxonomy, ontology, metadata) and knowledge retrieval (RAG) with chunking, embedding, and grounding for LLMs
- Experience designing end-to-end content/context lifecycles including ingestion, enrichment, indexing, and production deployment
- Hands-on experience prototyping and experimenting with modern AI and retrieval frameworks, vector and search technologies
- Ability to translate ambiguous business challenges into architecture problems and communicate findings clearly to technical and executive audiences
- strong communication across technical and executive stakeholders
- problem solving with ambiguity
- mentoring and teamwork
- natural language processing
- information retrieval
- large language models
