Senior AI Product Knowledge Architect

Job Description

Location: Chicago, IL preferred; remote candidates considered

\n

Work Arrangement: Hybrid, onsite Tuesday–Thursday for Chicago-based candidates

\n

Pay: 75-85hr/w2

\n

Duration: Approximately 16 weeks, with potential for extension

\n

\n

\n

Our client is advancing a next-generation AI-powered product experience that combines healthcare data, proprietary research, methodologies, and intelligent insights to support strategic decision-making.

\n

\n

They are seeking a hands-on Senior AI Product Knowledge Architect / AIDLC Enablement Lead to transform fragmented product, research, data, and business knowledge into structured, validated, reusable assets that enable AI-driven workflows, ontology development, and intelligent orchestration.

\n

\n

This delivery-focused role will collaborate across Product, Data Science, Engineering, Ontology, and subject-matter expert (SME) teams to establish authoritative knowledge, resolve inconsistencies, formalize business logic, and develop practical standards that support an AI-enabled development lifecycle (AIDLC).

\n

\n

Key Responsibilities

\n

\n
• Inventory and organize product documentation, research, methodologies, business rules, terminology, and data definitions across enterprise knowledge repositories.
\n
• Identify knowledge gaps, duplication, conflicting definitions, and ambiguities; partner with SMEs to validate and establish authoritative information.
\n
• Develop AI-ready knowledge assets, including structured Markdown documentation, taxonomies, synonym maps, business-question catalogs, data crosswalks, entity relationships, and business rules.
\n
• Translate product concepts, analytical intent, data relationships, and domain methodologies into structured inputs for ontology, data science, and engineering teams.
\n
• Facilitate SME review sessions, document decisions, resolve discrepancies, and track outstanding questions and validation requirements.
\n
• Establish reusable templates, repository standards, versioning conventions, stewardship models, and lightweight review and approval workflows.
\n
• Apply AI-assisted knowledge extraction using large language models (LLMs), ensuring human validation, source traceability, and reliable information provenance.
\n
• Deliver prioritized knowledge assets within the first 30–90 days and recommend a roadmap for ongoing AI enablement and ontology development.
\n

\n

\n

Required Qualifications

\n

\n
• 5+ years of relevant experience in product operations, information architecture, knowledge management, data governance, business analysis, semantic modeling, or a related field.
\n
• Proven ability to transform fragmented or unstructured information into organized, validated, reusable business or product knowledge.
\n
• Experience developing taxonomies, controlled vocabularies, metadata models, semantic crosswalks, business rules, or structured information architectures.
\n
• Strong ability to translate complex business concepts, data definitions, methodologies, and workflows into clear, precise documentation.
\n
• Experience collaborating across Product, Data, Engineering, and business subject-matter experts.
\n
• Hands-on proficiency with structured documentation, Markdown, spreadsheets, and collaborative knowledge repositories.
\n
• Excellent analytical, writing, facilitation, and problem-solving skills, including the ability to distinguish verified facts from assumptions and unresolved decisions.
\n
• Demonstrated ability to work independently, prioritize deliverables, manage dependencies, and produce measurable results within a short engagement.
\n

\n

\n

Preferred Qualifications

\n

\n
• Experience with generative AI, retrieval-augmented generation (RAG), knowledge graphs, ontology development, semantic layers, or intelligent orchestration.
\n
• Familiarity with AI-enabled product development, AIDLC practices, data products, or AI product operations.
\n
• Experience in healthcare analytics, healthcare data, or other complex, highly governed data environments.
\n
• Exposure to Confluence, SharePoint, Adobe DAM, Databricks, enterprise search, vector search, or AI context libraries.
\n
• Experience converting proprietary research, domain expertise, or institutional knowledge into structured, machine-readable assets.
\n

\n

\n