AI Architect
talentolaOak Park (IL)
About the role
Role: AI Architect
Location:
Chicago, IL(Hybrid- 3 days/week in office)Contract role Looking for 12-15 Years minimum experience Mandatory skills· Stardog, Agentic AI, Knowledge Graph, ML Stardog experience is not a mandatory requirement, Our primary focus is on candidates with strong hands-on experience in Agentic AI and Knowledge Graph technologies.
What is in it for you?
As an AI Architect, you will be a part of an Agile team to build healthcare applications and implement new features while adhering to the best coding development standards.
Responsibilities:
-· Define the end-to-end Agentic AI and Knowledge Graph architecture.· Design supervisor, planner, specialized agent, tool-use, and human-in-the-loop patterns.· Define integration with VIP data platform, Orkes workflows, Databricks, and Unity Catalog.· Design the Stardog Knowledge Graph model for schemas, mappings, recipes, rules, lineage, and contractual controls.· Establish AI security, HIPAA, PHI protection, tenant isolation, and contract-honoring guardrails.· Define standards for grounding, explainability, confidence scoring, evaluation, and observability.· Guide reusable agent skills for source discovery, Epic mapping, recipe generation, quality, and remediation.· Review solution designs, technical deliverables, and production-readiness.
Skills Required:
· Enterprise architecture for Agentic AI, GenAI, ML, and data platforms.· Multi-agent orchestration and human-in-the-loop architecture.· Knowledge Graph, ontology, semantic modeling, and graph-based retrieval.· RAG and hybrid retrieval using graph, vector, and structured data.· Healthcare data, HIPAA, PHI, EHR/Epic, and clinical-data integration knowledge.· Data engineering, metadata management, lineage, and data-quality concepts.· API, microservices, event-driven, security, and cloud architecture.· Strong stakeholder communication and architecture-governance skills. Tool & Technology Exposure Azure AI Foundry, Lang Chain, Deep Agents, Stardog, Orkes, Azure Databricks and PySpark, MLflow Unity Catalog Azure Blob Storage Azure Document Intelligence Dynatrace and Open Telemetry Git Hub and CI/CD Python, SQL, REST APIs, FHIR, HL7
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.
More like this