Agentic AI Engineer; Not Remote - Kennesaw, GA

Agentic AI Engineer (Not Remote) - Kennesaw, GA

Kennesaw, GA, USA

Full Time

United Contractor Services (UCS) is a national specialty subcontractor and a Top 50 Walls and Ceilings contractor in North America. We self-perform commercial interior construction across metal framing, drywall, acoustical ceilings, EIFS, stucco, painting, and Division 8 & 10 Specialties. As we continue to grow across multiple markets, we're looking for an Agentic AI Engineer to help us continue our growth.

We operate a portfolio of businesses united by a single belief: technology, applied well, is a competitive advantage. We run a modern stack-Microsoft 365, Entra , Intune, Azure (Functions, Table Storage, Entra Domain Services), Procore, and custom integrations built on  and the Microsoft Graph. We are now investing in agentic AI as a first-class capability across our operating companies, and we are hiring an Agentic AI Engineer to build it.

This is a builder role. You will design, ship, and maintain production AI agents that automate real business processes-document intake, data extraction, system-to-system synchronization, internal copilots, decision-support tools, and workflow orchestration-across multiple business units. You will work directly with the Director of Technology and have a clear line of sight from problem to deployed solution. We are not looking for a PowerPoint AI strategist.

We are looking for someone who writes the code, ships the agent, and owns the outcome.

• Design and build production agentic AI systems: tool calling, multi-step reasoning, sub-agent orchestration, memory, retrieval, and human-in-the-loop checkpoints.
• Partner with leadership and operators across our business units to identify high-value automation opportunities and translate them into shipped agents.
• Build and maintain integrations across our existing stack-Microsoft Graph, Entra, SharePoint, Teams, Procore, Azure Functions, , and third-party APIs.
• Develop rigorous eval pipelines and observability for every agent in production-cost monitoring, quality tracking, failure-mode detection, and regression testing.
• Implement secure agent identity and authorization patterns: managed identities, service principals, OAuth2 flows, least-privilege Graph permissions, and audit logging.
• Establish and uphold AI governance standards across our entities-data handling, model selection, prompt management, version control, and rollback procedures.
• Document architectures and decisions clearly so the systems you build outlive any single engagement.
• Stay current on the agentic AI landscape (Claude, OpenAI, Azure AI Foundry, Copilot Studio, Lang Graph, MCP, etc.) and make pragmatic platform recommendations.

• 3–5 years of professional software engineering experience, with at least 1 year shipping production AI/LLM systems (not prototypes, not demos).
• Strong proficiency in Python and/or Type Script.
• Hands-on experience with at least one major agent framework or SDK:
  Anthropic Claude SDK, OpenAI Agents SDK, Lang Graph, Vercel AI SDK, Semantic Kernel, or Azure AI Foundry.
• Real experience building and interpreting eval harnesses. You can show us how you measure whether an agent is working.
• Working knowledge of the Microsoft cloud stack:
  Azure Functions, Microsoft Graph API, Entra  registrations, OAuth2, and managed identities.
• Backend and integration engineering chops: REST APIs, webhooks, queues, state management, and authentication patterns.
• Strong written communication and the ability to explain trade-offs to a technical leader making investment decisions.
• Comfortable working on-site in Kennesaw, GA.

• Production experience with Microsoft Copilot Studio, Power Automate, or Azure AI Foundry.
• Experience with Model Context Protocol (MCP) servers or comparable tool-server architectures.
• Familiarity with retrieval-augmented generation (RAG) over enterprise document stores (SharePoint, One Drive, Confluence, etc.).
• Experience working in a multi-entity or multi-tenant environment with cross-cutting identity and data concerns.
• Dev Ops/IaC exposure:
  Bicep, Terraform, Git Hub Actions, or Azure Dev Ops pipelines.
• Familiarity…