Lead Agentic AI Engineer-US Remote - US-OH,Columbus

Company Overview Imagine Everything. Build the Future with Hexion. At Hexion, we push boundaries, rethink possibilities, and create real impact. We activate science to deliver progress—developing breakthrough solutions that strengthen industries, protect communities, and drive a more sustainable future.

This is where bold thinkers, problem-solvers, and innovators come together to shape what’s next. Whether you’re engineering advanced materials, transforming manufacturing technologies, or leading strategic innovation, your ideas and actions leave a lasting mark. We cultivate an inclusive culture of growth, collaboration, and accountability, ensuring every contribution propels us forward.

We don’t follow the status quo—we challenge it, disrupt it, and improve it. Every role at Hexion is part of something bigger. We invest in innovation, sustainability, and continuous development—equipping you with the tools, training, and opportunities to excel. With an unwavering commitment to safety, partnership, belonging, and impact, we empower you to lead change and strengthen industries worldwide. Your Future Starts Here. If you’re ready to push limits, reimagine what’s possible, and create the extraordinary, Hexion is where you belong.

Anything is possible when you imagine everything. **Job Responsibilities**

• Serve as the engineering lead for Agentic AI delivery across Supply Planning and Manufacturing — owning the design, development, and deployment of production-grade AI agent solutions.
• Architect and build multi-agent AI systems using Azure AI Agent Service, AutoGen, Semantic Kernel, and/or LangChain/LangGraph — including orchestrator-executor patterns, tool calling, memory management, and agent coordination.
• Implement the MCP to surface enterprise data as structured context for AI agents operating in supply chain and manufacturing workflows.
• Build and deploy generative AI solutions on Azure AI Foundry — RAG-based knowledge agents, decision support for forecasting and capacity planning, and document intelligence for maintenance work orders and recipes.
• Design and deliver AI copilots and topic-based agents using Microsoft Copilot Studio — enabling Supply Planning and Manufacturing teams to access insights and take action directly from Teams and Outlook.
• Act as the AI delivery owner for agentic use cases — scoping business problems with stakeholders, defining agent capabilities and tool surfaces, prioritizing the roadmap, and driving adoption.
• Apply emerging agentic AI patterns — including ReAct, Plan-and-Execute, reflection, and human-in-the-loop — for supply chain and operational use cases.
• Partner with Supply Chain leadership, Demand Planning, Process Engineering, Maintenance Ops, and Plant teams to identify, scope, and deliver AI use cases that influence operational decisions.
• Define and maintain AI agent governance — prompt versioning, tool auditing, evaluation frameworks, observability, and safety guardrails for production deployments.
• Develop on Azure Databricks — PySpark and SQL against gold/platinum Delta tables, notebooks for transformation and feature work, and orchestration via Workflows.
• Build and maintain Power BI reports and semantic models that serve as grounding data for AI agents and executive dashboards across Supply Planning and Manufacturing.
• Own Supply Chain AI metrics alignment cadence — keeping priorities, status, and roadblocks visible to Supply Chain and Manufacturing leadership.
• Mentor analysts and engineers on agentic AI design patterns, MCP, and AI delivery best practices.

Minimum Qualifications Education & Experience (one of the following):

• Master’s degree in Mathematics, Computer Science, Data Science, Information Systems, Engineering, or a related field with 5+ years of relevant analytics / AI experience, OR
• Bachelor’s degree in Chemical, Industrial, Computer Science, or related fields with 8+ years of relevant analytics / AI experience.

Technical

• Hands-on experience with the MCP — building or consuming MCP servers/clients; ability to expose enterprise data sources (databases, APIs, SharePoint, ERP) as MCP tools for AI agents.
• Hands-on experience with multi-agent system design — designing and implementing multi-agent architectures; orchestrator-executor patterns, tool calling, memory management, and agent coordination using AutoGen, Semantic Kernel, LangChain/LangGraph, or Azure AI Agen…