Solutions Architect - AI

RADcube - A NLogix Company•Indianapolis, IN

About The Position

The Solutions Architect - AI owns the technical design of how enterprise business knowledge is captured, structured, and served to AI systems so they can answer business questions accurately. The role designs the domain context model, context repository, and evaluation harness used to measure AI accuracy before and after context is added. It also designs agentic automation and a playbook to accelerate onboarding of additional data domains. The architect sets technical direction for a team that includes a techno-functional architect, a data and AI engineer, a validation engineer, and a business analyst, and presents progress to client sponsors weekly. The role covers context architecture and domain modeling; architecture and integration of a business context repository; AI evaluation and accuracy measurement; agentic automation and scale; and client leadership and knowledge transfer. The architect works with client program leads, data owners, and sponsors to confirm scope, success criteria, and priorities, leads demonstrations and incremental releases, guides business analysts in structuring testable questions, and provides knowledge transfer and handover documentation.

Requirements

  • Bachelor's degree in computer science, Data Science, Information Systems, or a related field, or equivalent experience.
  • 8+ years in data architecture or solutions architecture, including 3+ years designing AI or LLM solutions for production use.
  • Hands-on experience with retrieval-augmented generation, context or prompt engineering, and LLM evaluation, including ground-truth sets, automated grading, and rubric scoring.
  • Experience designing ontologies, semantic layers, or knowledge graphs, and working with business glossaries and metadata catalogs.
  • Strong SQL and data modeling skills, including the ability to verify join paths, grain, and aggregation logic.
  • Proficiency in Python for evaluation runners, pipelines, and automation.
  • Experience with agentic frameworks and orchestration, including human-in-the-loop review design.
  • Working knowledge of data classification and governance for PII and regulated data.
  • Clear communication skills, including the ability to run weekly demos for senior sponsors and translate business questions into testable requirements.

Nice To Haves

  • Life sciences or pharmaceutical data experience, including GxP-regulated data.
  • Experience with Claude or other enterprise LLM platforms.
  • Graph database experience, for example Neo4j or RDF/OWL.
  • Cloud certification in AWS, Azure, or GCP.
  • Active client system credentials for immediate mobilization.

Responsibilities

  • Define the Domain Context Model, including the context elements and minimum standards required for a data product to be context complete.
  • Design the domain ontology, including business concepts, relationships, hierarchies, and synonyms, and map it to data products, the client's knowledge graph, and semantic layer.
  • Assess existing metadata, definitions, and data classifications, and address gaps that block business context.
  • Establish ontology ownership, review, and change processes to keep context current.
  • Architect a Business Context Repository in a client-approved environment and harden it to client security and data standards.
  • Integrate the repository with the client's context injection layer, metadata registry, catalogs, and graph without rebuilding components the client already owns.
  • Align access controls with dataset classification.
  • Deliver source code, configuration, and runbooks to the client repository.
  • Design an evaluation harness with ground-truth question and answer sets, an evaluation runner, and grading using numeric match, query-result comparison, and rubrics.
  • Build a failure-mode taxonomy and scoring rubric for AI evaluation.
  • Use Claude or another approved LLM to generate and score answers, iterate on context, and retest to measure improvement.
  • Report before-and-after accuracy by dataset, question type, and failure mode; assess data-product AI readiness and identify remediation.
  • Design agentic workflows, orchestration patterns, and human-in-the-loop controls to draft, review, and refresh context at scale.
  • Automate intake from metadata registries, catalogs, workshop outputs, BI reports, and usage logs, and incorporate feedback from user questions.
  • Build scheduled refreshes and staleness flags to prevent context drift.
  • Author the domain onboarding playbook, effort model, and prioritized roadmap for onboarding additional domains across a large data estate.
  • Serve as technical lead with client program leads, data owners, and sponsors to confirm scope, success criteria, and priorities.
  • Lead weekly demonstrations and incremental releases aligned with the client's release calendar.
  • Guide business analysts in turning ambiguous business requests into structured, testable questions.
  • Run knowledge transfer sessions and produce handover documentation.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service