AI Architect / Lead - Enterprise Generative AI (Azure)

Job Description: AI Architect / Lead – Enterprise Generative AI (Azure)

Location: Onsite – Lansing, Michigan

Role: AI Architect / Technical Lead

Work Model: Onsite

Technology Focus: Microsoft Azure, Azure AI Foundry, Agentic AI, RAG, MCP, Azure OpenAI

Job Summary

We are seeking an experienced AI Architect / Technical Lead to design, architect, and deliver enterprise-grade Generative AI solutions using Microsoft Azure AI technologies. The ideal candidate will have strong expertise in Azure AI Foundry, agentic AI architectures, Retrieval-Augmented Generation (RAG), multi-agent orchestration, enterprise integrations, and responsible AI implementation.

The candidate will lead the development of secure, scalable, permission-aware AI assistants integrated with enterprise platforms such as SharePoint, ServiceNow, Microsoft Teams, and Microsoft 365 Copilot.

This role requires strong hands-on engineering capabilities, architecture leadership, and experience delivering production-ready AI solutions with enterprise-grade security, governance, observability, and deployment practices.

Key Responsibilities

1. Enterprise GenAI Architecture

\n
• Architect and deliver enterprise AI assistants using Azure AI Foundry and Responses API agents.
\n
• Evaluate Microsoft Copilot Studio and conduct proof-of-concept implementations or side-by-side technology comparisons where appropriate.
\n
• Define scalable, secure, and maintainable GenAI architectures aligned with enterprise standards.
\n

2. Retrieval-Augmented Generation (RAG)

\n
• Design and implement enterprise RAG pipelines using Azure AI Search.
\n
• Implement hybrid search, vector embeddings, semantic ranking, and relevance optimization.
\n
• Build permission-aware retrieval mechanisms with document-level access control inherited from source systems.
\n
• Integrate enterprise content repositories such as SharePoint and digital asset management platforms.
\n

3. Agentic AI and MCP Integrations

\n
• Engineer agentic workflows connecting AI agents with enterprise systems through MCP servers and tool integrations.
\n
• Integrate platforms such as ServiceNow using secure APIs and MCP-based architectures.
\n
• Implement Microsoft Entra ID SSO, OAuth, and on-behalf-of (OBO) authentication flows.
\n
• Ensure end-to-end user identity propagation and authorization across agent interactions.
\n

4. Multi-Agent Orchestration

\n
• Design multi-agent architectures with intent classification, routing, delegation, and specialized sub-agents.
\n
• Implement predictable fallback, retry, regeneration, and error-handling strategies.
\n
• Develop coordinated agent workflows for enterprise automation and decision intelligence.
\n

5. Conversation Management and Memory

\n
• Design conversation state management and persistent memory using Azure Cosmos DB.
\n
• Support context-aware multi-turn conversations while maintaining grounding, consistency, and session continuity.
\n
• Implement appropriate memory retention and lifecycle management strategies.
\n

6. AI Safety, Security, and Compliance

\n
• Implement configuration-driven AI safety and compliance controls.
\n
• Integrate Azure AI Content Safety and Prompt Shields.
\n
• Implement PII/PHI detection, masking, and sensitive information handling.
\n
• Develop sensitive-statement detection mechanisms, including HR escalation workflows where required.
\n
• Ensure enterprise security, privacy, responsible AI, and regulatory compliance.
\n

7. Azure AI Engineering and Observability

\n
• Develop using Azure SDKs across AI inference, search, storage, identity, and monitoring services.
\n
• Implement application monitoring, distributed tracing, and observability using OpenTelemetry and Azure Application Insights.
\n
• Optimize performance, scalability, reliability, and operational costs.
\n

8. Prompt Engineering and Evaluation

\n
• Design, maintain, and optimize prompt templates for different agent personas and business use cases.
\n
• Implement prompt versioning alongside evaluation datasets.
\n
• Establish automated evaluation frameworks for groundedness, relevance, safety, and response quality.
\n
• Implement evaluation-gated releases with automated testing and security reviews before environment promotion.
\n

9. Deployment and DevOps

\n
• Deploy enterprise AI assistants to Microsoft Teams and Microsoft 365 Copilot.
\n
• Provision Azure infrastructure using Terraform and Infrastructure as Code (IaC).
\n
• Build and maintain CI/CD pipelines using Azure DevOps.
\n
• Establish development, testing, staging, and production deployment processes.
\n

Required Technical Skills

\n
• Microsoft Azure AI Foundry
\n
• Azure OpenAI / Responses API
\n
• Azure AI Search
\n
• Retrieval-Augmented Generation (RAG)
\n
• Vector Search, Hybrid Search, and Semantic Ranking
\n
• Agentic AI and Multi-Agent Orchestration
\n
• Model Context Protocol (MCP)
\n
• Microsoft Entra ID, OAuth 2.0, and OBO Authentication
\n
• Azure Cosmos DB
\n
• Azure AI Content Safety and Prompt Shields
\n
• Python and Azure SDKs
\n
• REST APIs and enterprise integrations
\n
• SharePoint, ServiceNow, and Microsoft Graph
\n
• OpenTelemetry and Azure Application Insights
\n
• Terraform and Azure DevOps
\n
• Microsoft Teams and Microsoft 365 Copilot
\n

Preferred Qualifications

\n
• Experience designing and implementing enterprise-scale Generative AI platforms.
\n
• Strong understanding of enterprise security, identity management, and access control.
\n
• Experience building production-grade RAG and agentic AI applications.
\n
• Knowledge of AI governance, responsible AI, and compliance frameworks.
\n
• Experience with automated LLM evaluation, testing, and release management.
\n
• Strong architecture documentation, technical leadership, and stakeholder communication skills.
\n

Ideal Candidate Profile

The ideal candidate will be a hands-on AI Architect with the ability to translate enterprise business requirements into scalable GenAI solutions. They should have experience leading architecture decisions, developing production-ready AI applications, integrating enterprise systems, and establishing security and governance standards for enterprise AI adoption.

Work Location: Lansing, Michigan (Onsite)

Position: AI Architect / Lead – Enterprise Generative AI (Azure)