Production AI Engineer: Agentic Systems & Automation

United Contractor Services, LLC; Kennesaw (GA); Presencial; USD 120.000 - 180.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Health coverage

Dental coverage

Vision coverage

Retirement plan

Paid time off

Learning budget

Descripción de la vacante

United Contractor Services is seeking an engineer to build production AI agents that perform real work across our business. This hands-on role requires coding, deploying, and owning agent performance on-site at our Kennesaw headquarters, GA.

You’ll integrate with Microsoft 365 and external APIs, set up evaluation pipelines, and craft clear architecture documentation for long-term maintenance. You’ll collaborate with leadership to identify automation opportunities, ensure secure identity

Formación

• 3 to 5 years of professional software engineering experience, including at least 1 year delivering AI/LLM systems in production.
• Strong Python and/or TypeScript skills.
• Hands-on work with at least one major agent framework or SDK, such as the Anthropic Claude SDK, OpenAI Agents SDK, LangGraph, Vercel AI SDK, Semantic Kernel, or Azure AI Foundry.
• Real experience building eval harnesses and interpreting the results.
• Working knowledge of Azure Functions, Microsoft Graph API, Entra ID app registrations, OAuth2, and managed identities.
• Solid backend and integration skills: REST APIs, webhooks, queues, state management, and authentication patterns.
• Clear writing and the ability to lay out trade-offs for a technical leader making investment calls.
• Able to work on-site daily in Kennesaw, GA.

Responsabilidades

• Architect and ship production agentic systems using tool calling, multi-step reasoning, sub-agent orchestration, memory, retrieval, and human-in-the-loop review points.
• Work with leadership and operators in each business unit to find automation opportunities worth pursuing, then deliver agents that capture them
• Connect agents to our existing environment, including Microsoft Graph, Entra, SharePoint, Teams, Procore, Azure Functions, Make.com, and outside APIs
• Build secure identity and access patterns for agents: managed identities, service principals, OAuth2 flows, least-privilege Graph permissions, and audit logging
• Stand up evaluation pipelines and observability for every production agent, covering cost, output quality, failure modes, and regression testing
• Track down problems early and keep agents performing as the business and the models change
• Set and maintain AI governance standards across our companies for data handling, model selection, prompt management, versioning, and rollback
• Write clear documentation of architecture and decisions so your systems can be maintained long after they're built
• Follow the agentic AI space closely (Claude, OpenAI, Azure AI Foundry, Copilot Studio, LangGraph, MCP, and others) and give practical recommendations on which platforms to use

Conocimientos

Python

TypeScript

Agent frameworks

Eval harnesses

Azure Functions

Microsoft Graph API

OAuth2

REST APIs

Webhooks

Communication

Herramientas

Anthropic Claude SDK

OpenAI Agents SDK

LangGraph

Vercel AI SDK

Semantic Kernel

Azure AI Foundry

Descripción del empleo

United Contractor Services is seeking an engineer to build production AI agents that perform real work across our business. This hands-on role requires coding, deploying, and owning agent performance on-site at our Kennesaw headquarters, GA.

You’ll integrate with Microsoft 365 and external APIs, set up evaluation pipelines, and craft clear architecture documentation for long-term maintenance. You’ll collaborate with leadership to identify automation opportunities, ensure secure identity