AI Applications Developer

About the role

Lead Hexion’s enterprise Agentic AI and automation strategy—architecting and scaling agentic AI capabilities, identifying automation opportunities across all business functions, championing AI fluency and a learning culture, and overseeing the execution and KPI governance of automation initiatives to deliver measurable business value across the organization.

Job Responsibilities

• Build AI-powered applications that deliver agentic and generative AI capabilities to business users across commercial, supply chain, manufacturing, and R&D functions.
• Develop and tune Retrieval-Augmented Generation (RAG) pipelines over unstructured content such as product specs, Safety Data Sheets, standard operating procedures, emails, and meeting transcripts — using parsing (Azure Document Intelligence, Unstructured), chunking, embeddings, hybrid search, and reranking.
• Create domain-specific tools and connectors (including Model Context Protocol servers) that expose enterprise systems — ERP, planning, analytics, content management, and custom APIs — as safe, well-documented actions for AI agents to call.
• Build user-facing surfaces with Microsoft Copilot Studio, Power Apps, Teams apps, Streamlit, or React — including chat interfaces, approval workflows, and result-review screens.
• Implement data validation and guardrails at every tool boundary: schema checks, business-rule validation, content safety, PII handling, and explicit user confirmation for write operations.
• Partner with product owners and subject-matter experts to gather requirements, translate workflows into agent execution plans, prototype rapidly, demo, gather feedback, and iterate.
• Support deployment and operations of the applications you build: package for production on Azure AI Foundry or Container Apps, add tracing and logging, monitor usage and quality, and respond to production issues.
• Apply prompt engineering and evaluation to measure application quality — build test cases, run LLM-as-judge evals, and track regressions over time.
• Document use cases, tools, and playbooks so applications remain maintainable and extensible by the team.
• Collaborate across globally distributed teams through code reviews, pair programming, and shared technical standards.

Minimum Qualifications

• Bachelor’s degree in Computer Science, Engineering, Information Systems, or a related technical field — or equivalent hands-on experience.
• 5+ years of professional software development or data/analytics engineering experience, including recent hands-on work with LLMs or AI-powered applications (professional projects, internships, or substantive personal projects).
• Strong proficiency in Python and comfort with TypeScript or JavaScript for front-end work.
• Working knowledge of at least one AI/agent framework: LangChain, LangGraph, LlamaIndex, Semantic Kernel, AutoGen, or CrewAI.
• PRACTICAL experience with LLM APIs (Azure OpenAI, Anthropic Claude, OpenAI, or Hugging Face) and structured outputs.
• Hands-on RAG experience — document parsing, chunking, embeddings, and hybrid retrieval — with at least one vector database.
• Comfort integrating with enterprise APIs such as ERP, BI platforms, SharePoint or Microsoft Graph, Teams, and REST/GraphQL services.
• Solid SQL skills and working familiarity with a modern data platform (Databricks, Snowflake, or equivalent).
• Self-directed learner who stays current with a fast-moving field, can teach themselves new frameworks with minimal guidance, and ships working software without hand-holding.
• Strong problem-solving, communication, and documentation skills; comfortable demoing to business stakeholders and gathering requirements directly from subject-matter experts.
• Solid understanding of Git, CI/CD, and basic DevOps workflows.

Preferred Qualifications

• HANDS-ON experience with Microsoft Copilot Studio, Microsoft 365 Copilot extensibility, or Power Platform (Power Apps, Power Automate).
• Experience with Azure AI Foundry agents or Palantir AIP Logic / Workshop applications.
• FAMILIARITY with Model Context Protocol (MCP), tool/function calling, and prompt registries.
• EXPERIENCE with LLM observability and evaluation tooling — LangSmith, Langfuse, Arize, or Weights & Biases.
• UX sensibility — ability to design clean, low-friction chat and approval interfaces that business users actually adopt.
• EXPERIENCE with Docker, containerized deployments, and infrastructure-as-code (Terraform or Bicep).
• PUBLIC portfolio — GitHub projects, technical blog posts, or community contributions — demonstrating curiosity and hands-on experimentation in generative or agentic AI.
• PRIOR experience delivering business applications in process industries, manufacturing, supply chain, or commercial analytics.