AI Solutions Engineer / Architect at Lantern RE a US-based real estate (remote, project-based)

Hire5 • New York, NY

7d • Remote

About The Position

Lantern Real Estate Advisors + Partners is a growing real estate investment firm that runs entirely on Microsoft 365. Founded by experienced real estate professionals, the team now wants to move beyond generic AI tools and build something proprietary — a corporate-level AI agent that sits on top of their M365 environment, learns from every team interaction, and produces consistent, branded output across the whole organisation. The system is being built from scratch, with the Claude API as the reasoning engine and Azure as the infrastructure backbone.
ABOUT THE ROLE
We're looking for a mid-to-senior AI/cloud engineer to design and build this system end-to-end. You'll work directly with Matthew (co-founder and your day-to-day contact) and an internal IT lead. This is a greenfield project — there's no legacy system to untangle, just a clear brief and a motivated client who wants something working within three months.
The core challenge is elegant orchestration: connecting Claude's API to Microsoft 365's data layer, ensuring all 25 users share a single knowledge base rather than fragmented individual sessions, and making the AI's output look and feel unmistakably like Lantern RE — right down to the branded PowerPoint templates.
Because the AI landscape is moving fast, Matthew wants the architecture to be model-agnostic from day one. If a better model comes along, swapping it in should be straightforward.

WHAT YOU'LL BUILD
The project is delivered in three phases:
Phase 1 — Foundation: Azure infrastructure provisioned in the client's own tenant, M365 SSO via Entra ID, and a working portal. Claude API connected with a locked, version-controlled system prompt; Word and Outlook integrations via Microsoft Graph
Phase 2 — Memory layer: Azure AI Search deployed; interaction logging and indexing pipeline built so the system starts accumulating firm-specific knowledge from real usage
Phase 3 — Full M365: PowerPoint, Teams, SharePoint, and Excel integrations added; branded output templates locked in; role-based permissions and admin controls; team onboarding

Requirements

• 3+ years of experience building on Microsoft Azure — resource provisioning, Entra ID / Azure AD, app registrations, security policies
• Hands-on experience with the Microsoft Graph API for M365 integrations (Word, Outlook, SharePoint, Teams)
• Experience integrating LLM APIs (Claude, OpenAI, or similar) into production systems, including prompt design and governance
• Familiarity with RAG pipelines and vector/AI search (Azure AI Search or equivalent)
• Ability to design model-agnostic orchestration architectures that can swap underlying LLMs without rebuilding the stack
• Experience with interaction logging, knowledge base construction, and indexing pipelines
• Independence: comfortable owning a greenfield project with limited internal technical support on the client side
• Communication: fluent English, proactive with updates, clear when scoping risks arise
• Accountability: you set the expectations, you deliver on them

Nice To Haves

• Background in real estate, finance, or professional services — the use cases are contract- and document-heavy
• Experience building Office Add-ins (Word/Outlook task panes)
• Familiarity with Microsoft Power Platform (Power Automate, Copilot Studio)

Responsibilities

• Architect and build the agentic orchestration layer on top of Microsoft 365, designed to be LLM-agnostic from the start
• Set up and configure Azure infrastructure (resource groups, Entra ID app registration, Azure AI Search, storage)
• Integrate the Claude API with a locked system prompt; implement interaction logging so all 25 users contribute to a shared organisational knowledge base
• Connect Word and Outlook via Microsoft Graph in Phase 1; expand to PowerPoint, Teams, SharePoint, and Excel in Phase 3
• Build branded document output templates (logo, colour palette, formatting) that lock in on all AI-generated exports
• Implement role-based permissions, search guardrails, and an admin control panel
• Provide regular project check-ins with the co-founder (1–2 hour daily overlap window)
• Advise on scope and timeline — if something needs more time, say so early

Benefits

• Remote contract role — work from anywhere with a reliable connection
• Flexible hours with a 1–2 hour daily overlap window for project check-ins (no fixed timezone required)
• Hourly rate, with scope to extend beyond the initial 3-month engagement if the project grows
• Direct access to the co-founder — no layers of management, fast decisions
• A genuinely interesting technical problem: greenfield AI infrastructure on M365 for a firm with real institutional data to work with

What This Job Offers

• Career Level: Mid Level
• Education Level: No Education Listed