Lead AI Engineer

Pogue Construction•McKinney, TX

1d•Onsite

About The Position

The Lead AI Engineer delivers and operationalizes Pogue Construction Company’s enterprise AI capabilities, taking approved backlog items and validated prototypes through production as secure, reliable, well-documented solutions. The role is part of the AI production team and leads secure retrieval, application integrations, reusable AI services, and the engineering needed to deploy and support them. Full-stack development is a core skill, used to carry applications from prototype through production. This is a hands-on technical leadership role. The Lead AI Engineer partners closely with the Enterprise Data Architect, who leads enterprise data architecture, governed data products, data pipelines, and shared semantic models, and builds on that foundation in Microsoft Fabric and the enterprise knowledge foundation. The role leads solution design through review with the Principal Solutions Architect, provides technical guidance to the AI production team, and works directly with business owners to support adoption and ensure the solutions are used.

Requirements

At least 5 years of professional software development experience, including full-stack web application development.
At least 2 years building and supporting AI- or LLM-integrated applications in production.
Demonstrated experience taking applications from prototype through production and ongoing support.
Hands-on experience building and operating production LLM applications, including RAG, embeddings, tool calling, and evaluation.
Experience designing reusable services or shared platform components.
Ability to explain a technical design, personal decisions made, tradeoffs, and how the result was validated.
Strong command of REST API design and enterprise integration.
Advanced SQL and relational data modeling.
Working knowledge of Microsoft Fabric, semantic models, and governed data products.
Advanced C# and .NET, including ASP.NET Core web APIs.
Production front-end experience in Blazor or a comparable component framework.
Experience with TypeScript or JavaScript, HTML, CSS, responsive design, and accessible design.
Advanced proficiency writing, reviewing, and troubleshooting code in VS Code.
Git-based collaboration, automated testing, and CI/CD experience.
Experience deploying and supporting applications in Azure or a comparable cloud.
Secure handling of credentials and data, including identity and role-based access.
Highly analytical thinking.
Strong organization and attention to detail.
Clear written communication and ability to communicate with a diverse group of professionals.
Internal and external customer service skills.
Ability to work individually and as part of a team.
Self-motivated and driven, with a positive attitude.
Willingness to learn and grow; ability to mentor and teach; curious and self-directed.
Minimum 20 hours of continuing education yearly.
Bachelor’s degree in computer science, software engineering, information systems, or a related field, or commensurate experience.

Nice To Haves

Azure AI Search, Azure API Management, OneLake, or Power BI.
React or another JavaScript front-end framework.
Agents, MCP integrations, workflow automation, or prompt or model lifecycle management.
Knowledge representation, semantic modeling, enterprise ontologies, or knowledge graphs, including Protégé, OWL, RDF, or SPARQL.
Containerized services, infrastructure as code, or cost management.
Experience with construction and project-control systems, or another operationally complex industry.

Responsibilities

Deliver and operationalize enterprise AI capabilities, including enterprise search, internal assistants, agents, and workflow automation.
Build and maintain reusable AI services for model access, retrieval, evaluation, logging, and guardrails.
Integrate approved models through APIs, structured outputs, and tool calling using Azure OpenAI or Azure AI Foundry.
Break approved backlog items into requirements, designs, acceptance criteria, and small, measurable releases.
Lead design reviews with the Principal Solutions Architect before development and carry approved designs through release and support.
Lead secure retrieval across structured data and approved documents, including permission-aware access, citations, versions, effective dates, and retrieval quality.
Lead application integrations connecting Pogue applications to enterprise systems, Fabric data, and AI services through secure APIs.
Partner with the Enterprise Data Architect, building on governed data products and shared semantic models in Microsoft Fabric.
Partner on Pogue’s knowledge foundation, bringing application needs into its objects, relationships, and definitions.
Build only on validated Gold-layer data and raise data gaps to the data team rather than working around them.
Take validated prototypes, including SME-built prototypes, through production as maintainable applications and reusable components.
Build responsive, accessible front ends in Blazor and C#, using TypeScript or JavaScript where needed.
Build back-end services and REST APIs in C# and .NET.
Deploy, monitor, and support Azure solutions, including Azure Static Web Apps, with CI/CD and Microsoft Entra ID authentication.
Set team standards for documentation, testing, code review, deployment, monitoring, and operating runbooks.
Design evaluations for accuracy, failure modes, access behavior, latency, cost, and usefulness, and own release recommendations.
Enforce identity, role-based access, data-classification, approved-model, logging, and human-approval requirements.
Apply secure development practices across front end, back end, and AI, including addressing prompt-injection, data-leakage, and agent-permission risks.
Work with business owners and subject-matter experts to understand decisions or workflows before selecting a technical approach.
Explain technical tradeoffs and feasibility in plain language to technical and nontechnical stakeholders.
Support adoption with concise guides, training materials, and follow-through after launch.
Support the AI Champions Network as solutions roll out to project teams.
Provide technical guidance to the AI production team, including Associate AI Engineers and interns, through pairing, code review, and design feedback.
Establish reusable engineering patterns and recommend improvements to team tooling and standards.