AI Solutions Architect

LOCATION: Durham, NC (Hybrid)

ABOUT US

Victra is Verizon’s largest premium retailer in the United States. We thrive on collaboration, innovation, and performance. Our mission is to “Connect technology to life in a trustworthy, fun, and profitable way”. We work closely with Verizon and our brand partners to deliver exceptional product offerings, promotions, and campaigns that drive in-store traffic and revenue.

JOB DESCRIPTION

Victra runs roughly 1,500 retail locations and is bringing its AI engineering capability in-house on the Microsoft stack: Azure AI Foundry, Copilot Studio, Power Platform, and ServiceNow, with open-source components (LangChain, Langfuse) where they earn their place. This role owns the technical architecture our agents are built on and the standards that keep them trustworthy in production. You will define the reference architecture, design the control plane (identity, scoped data access, audit, approval gates), set the evaluation and observability standard that separates production agents from demos, and provide the technical counterweight in every vendor conversation. This is a hands-on architect seat: you write reference implementations, sit in incident reviews, and carry delivery accountability alongside design authority. You will not be setting enterprise-wide technology strategy from a distance; you will be making a real agent platform work for 8,000 employees.

KEY RESPONSIBILITIES

• Own the reference architecture for agentic AI on the Microsoft stack: Foundry project structure, Agent Service, retrieval and grounding patterns, and integration patterns to ServiceNow, point-of-sale, and HR systems
• Design and enforce the control plane: Entra ID and RBAC boundaries, scoped data access per agent, network isolation, audit trails, and approval gates, working with IT Security and the AI governance owners
• Define the evaluation and observability standard for production agents: pre-production evaluators and red teaming, continuous evaluation of sampled production traffic, drift detection, and alerting
• Make and document the platform routing call per use case: Copilot Studio as the governed low-code layer, Foundry as the pro-code runtime, or another platform when the use case genuinely belongs there, chosen by governance posture and outcome
• Own the framework and observability standardization decision: when to use Foundry-native capabilities (Agent Service, built-in evaluators, tracing) versus open-source components running on Azure (LangChain or LangGraph, Langfuse), and how the two coexist without fragmenting the platform or the audit trail
• Set the standards for AI-assisted development and coding agents used by the engineering team, including guardrails for what they may touch
• Provide technical review of all vendor and SOW work, including explicit lock-in and maintainability checks
• Produce per-initiative build-versus-buy recommendations against the function's standards
• Write reference implementations and prototype code; mentor early-career AI engineers on architecture and patterns
• Participate in incident review for production agents and feed lessons back into the architecture

WHAT WE ARE LOOKING FOR

REQUIRED

• 5 to 10 years in software or cloud engineering with at least 3 years of Azure solution delivery
• Bachelor's degree in computer science, information systems, or a related field, demonstrating technical dedication, the ability to commit long term, and a strong critical-thinking foundation
• One or more AI or agent systems shipped to production with named users and a working evaluation loop; you can walk us through the architecture, what broke, and how you measured quality
• Deep, current Azure AI Foundry knowledge: the unified resource model, Agent Service and its networking requirements (egress subnets, private endpoints, DNS dependencies), model catalog governance, and RAG integration
• Strong Azure platform fundamentals: identity and RBAC, networking and private connectivity, monitoring, and cost management
• Hands-on coding ability (Python preferred)
• Working fluency with at least one open-source agent framework and LLM observability stack (LangChain or LangGraph, Langfuse, or similar) alongside platform-native tooling, with clear judgment about when each belongs
• Ability to run requirements conversations with non-technical stakeholders and defend trade-offs in plain language

PREFERRED

• Microsoft certifications preferred, not required: AZ-305 Azure Solutions Architect Expert; AI-102 or its successor AI-103 Azure AI Apps and Agents Developer Associate; AB-100 Agentic AI Business Solutions Architect a strong plus
• Experience with Copilot Studio and Power Platform, and with drawing the boundary between low-code and pro-code AI builds
• Experience defining evaluation harnesses or LLM observability (evaluators, red teaming, drift monitoring)
• Experience reviewing or managing technical vendor and SI engagements
• Retail, multi-site, or field-operations domain exposure

GROWTH PATH

• The architecture seat for an AI platform being built from the ground up, with direct visibility to senior leadership. As the platform and team scale, the role grows toward senior platform architecture ownership across the AI engineering function.

WHY JOIN US?

• Paid training and career development opportunities.
• Comprehensive health, dental, and vision insurance.
• 401k retirement plan.
• Tuition reimbursement.
• Employee discounts on Verizon services.
• Referral bonuses.
• Career pathing opportunities.

EQUAL OPPORTUNITY EMPLOYER

We're proud to be an equal opportunity employer - and celebrate our employees' differences, regardless of race, color, religion, gender, sexual orientation, gender identity, national origin, age, disability, or Veteran status. Different makes us better.