Deep understanding of AI, generative AI, agentic systems, LLMs, intelligent automation, and modern data architectures.
Experience designing and operating large-scale agentic or autonomous systems in production.
Expertise with:
Agent frameworks (LangChain, Semantic Kernel, AutoGen, etc.)
Vector databases and retrieval-augmented generation (RAG)
LLMOps, evaluation, and monitoring frameworks
Experience with **multi-agent coordination, planning, and memory architecture.**
Enterprise Data Architecture and Strategy: Deep expertise in cloud-native enterprise data platforms, lakehouse and analytical architectures, governed data products, data integration, interoperability, metadata management, data quality, lineage, and secure access across complex domains.
Semantic, Context, and Knowledge Architecture: Hands-on experience designing semantic and context layers, business vocabularies and metrics, ontologies, knowledge graphs, entity relationships and resolution, and reusable knowledge representations that connect enterprise data to AI.
Familiarity with RDF/OWL, SPARQL, SHACL, graph databases, and semantic modeling is highly valued.
AI on Enterprise Data and Conversational Analytics: Experience implementing trustworthy natural-language analytics, text-to-SQL with governed semantic definitions, RAG/GraphRAG, semantic retrieval, context engineering, and AI agents that query, reason over, and act on enterprise data.
Demonstrated attention to provenance, authorization, evaluation, explainability, and numerical accuracy.
Healthcare Data and Decision Intelligence: Ability to apply enterprise data, semantics, analytics, ML, and AI to provider data and analytics, utilization management, prior authorization, clinical interoperability (FHIR/HL7), medical cost management, shift-left payment integrity, value-based care, employer analytics, claims, and care management.
Experience connecting clinical, member, provider, benefit, contract, and policy data is especially valuable.