Principal Engineer, Agentic AI

vfc; Denver (CO); On-site; USD 150,000 - 190,000; Full time

Job summary

VF Corporation seeks a Principal Agentic AI Engineer to lead production-grade agentic AI development and empower citizen developers with governance. The role focuses on pro-code extensions, cross-platform integration, and scalable, secure agent architectures.

The position emphasizes governance, reusable components, and cost-aware practices across VF’s enterprise-wide AI initiatives.

Responsibilities

• Own the pro-code extension layer for Copilot Studio, building connectors and actions.
• Implement multi-agent orchestration and HITL workflows.
• Develop integration between Copilot Studio and Azure AI Foundry.
• Design enterprise-grade RAG pipelines and vector databases.
• Establish governance standards and cost-tracking.
• Architect secure, scalable agent platforms and connectors.
• Build observability with Application Insights and telemetry.

Skills

Copilot Studio

Azure AI Foundry

HITL

MCP server

Agentic AI

Governance

Integration connectors

Low-code development

Pro-code extension

Vector databases

Tools

Azure OpenAI Service

Semantic Kernel

Job description

At VF, we strive to foster a culture of belonging based on respect, connection, openness, and authenticity. So, before we get to the job details, take a minute to learn a little more about us - our values and our culture - visit VF Careers or www.vfc.com.

What will you do?

A day in the life of a Principal Agentic AI Engineer at VF looks a little like this.

The Principal Agentic AI Engineer is a hands‑on technical leader embedded in VF Corporation’s centralized Agentic AI team. This team operates as a cross‑brand, cross‑region Center of Excellence that builds and deploys AI agents for every brand in VF’s portfolio and every function in VF’s enterprise.

This role carries a dual mandate that is critical to VF’s agentic AI strategy:

1. Own the pro‑code development of production‑grade agentic AI, building custom agents, multi‑agent orchestration, complex integrations, and bespoke solutions that require deep engineering expertise.
2. Evangelize and enable low‑code development across brand and business functions, empowering citizen developers to build, extend, and maintain their own agents while establishing the guardrails, patterns, templates, and governance that make decentralized agent creation safe and effective.

You are the engineer who builds the hardest agents yourself and makes it possible for everyone else at VF to build the rest. You set the architectural patterns, create the reusable components, establish the integration connectors, and define the quality standards that the entire VF organization inherits.

Platform Polyglot: You think in terms of agent platforms and frameworks as a portfolio - the right tool for each job. Copilot Studio for enterprise productivity & Azure AI Foundry for custom builds.

Governance by Design: governance is what makes innovation scalable. Build guardrails into every template, every connector, and every training so that decentralized agent creation is safe.

Let’s break down that day‑in‑the‑life a bit more.

CORE PLATFORM RESPONSIBILITIES

Microsoft Copilot Studio - Low-Code Enablement & Pro-Code Extension

Own the pro‑code extension layer for Copilot Studio building custom connectors developing Power Platform dataflows and custom actions; and creating reusable component libraries.

Implement advanced Copilot Studio capabilities multi-agent orchestration, Model Context Protocol (MCP) server integration, human‑in‑the‑loop (HITL) approval workflows and Copilot Tuning.

Build and enforce governance standards: lifecycle management, naming conventions, environment management, DLP policies, Entra Agent ID configuration, telemetry and analytics, and cost tracking.

Develop the integration between Copilot Studio and Azure AI Foundry, creating seamless upgrade paths where agents that outgrow Copilot Studio’s capabilities.

Azure AI Foundry - Custom Agentic Application Development

Architect and build production‑grade custom agentic applications on Azure AI Foundry using Azure OpenAI Service, Azure AI Search, Azure AI Agent Service, Prompt Flow, and Semantic Kernel.

Build and maintain VF’s custom RAG pipelines and vector databases and develop agent evaluation and testing infrastructure on Azure: building task‑specific benchmarks, LLM‑as‑judge evaluation pipelines, red‑team testing harnesses, and regression test suites.

Implement agent observability, tracing, monitoring, Application Insights, and custom telemetry -providing VF’s Agentic AI team with real‑time visibility into performance, cost, error rates, and impact.

Contribute to VF’s responsible AI practices by implementing guardrails, content safety filters, PII detection and masking, prompt injection defenses, and bias mitigation across all Azure AI Foundry.

LOW‑CODE EVANGELISM & CITIZEN DEVELOPER ENABLEMENT

Design and deliver training for Copilot Studio, structured in tiers: Foundational (business analysts building first agents), Intermediate (power users adding custom connectors and knowledge sources), and Advanced (technical builders using MCP, HITL, and multi‑agent patterns).

Build and publish VF’s “Agent Developer Guide” and an agent template gallery - a curated library of pre‑built, governance‑approved agent design patterns, connector libraries, governance requirements, testing standards, and deployment checklists.

Track and govern developer adoption metrics: count, usage, business value delivered by decentralized agents, and quality/governance compliance rates-demonstrating the ROI.

Identify when citizen‑built agents are hitting the ceiling of low‑code capabilities and transition them to pro‑code solutions, either by extending with custom connectors or migrating to Azure AI Foundry.

TECHNICAL RESPONSIBILITIES

Architecture & Design

Design the integration layer between VF's agent platforms and enterprise systems of record using custom connectors, APIs, MCP servers, and event‑driven architectures.

Architect secure, performant RAG pipelines that ground VF's agents in enterprise knowledge with proper chunking, embedding, indexi