Realtor.com is looking for a Senior AI Platform Engineer to architect, build, and continuously improve the internal AI tooling foundation that powers safe, scalable AI adoption across the company. This role blends software engineering rigor with core enterprise platform management. You will be responsible for building the software frameworks, protocols, and developer harnesses that allow autonomous agents to interact safely, while simultaneously owning the operational health, access governance, maintenance, and license hygiene of our key AI tools (Portkey, Claude, Gemini, Devin, and Glean).
We are looking for a rigorous practitioner who advocates for software engineering excellence across the full Product Development Life Cycle (PDLC). You will leverage AI through spec-driven design, automation-driven provisioning, and robust platform maintenance, eliminating ad hoc ownership and freeing solution builders to focus on workflow design and delivery.
Top Reasons to Apply:
- Architect and Operate the AI Paved Path: Shape the enterprise AI productivity platform and the paved-path stack at Realtor.com, combining core platform engineering with daily operational excellence.
- Build the Operational Backbone for AI: Drive the programmatic adoption of emerging open protocols like the Model Context Protocol (MCP) while significantly maturing platform governance, access, and observability.
- Make a Company-Wide Impact: Enable safe AI adoption for all employees while systematically reducing stack fragmentation, vendor sprawl, and uncontrolled spend.
What You'll Do:
- Design & Implement Agentic Architecture: Build the core software platform, APIs, and SDKs that enable agentic use cases, focusing on orchestration, memory layers, and state management.
- Own Day-to-Day Platform Operations: Manage the operational lifecycles for Portkey, Claude, Gemini, Devin, and Glean, including provisioning, deprovisioning, access requests, license hygiene, and technical support workflows.
- Standardize AI Protocols & Connectors: Implement and extend emerging industry protocols and standards, including Model Context Protocol (MCP), Agent-to-Agent (A2A) communication, and Agentic Resource Definition (ARD).
- Engineer the LLM Gateway & Access Layer: Mature our LLM gateway layer (leveraging Portkey or custom infrastructure) to centralize model access, routing, semantic caching, deterministic guardrails, spend limits, rate limiting, and PII controls.
- Enforce Platform Governance via Code: Implement identity lifecycle management, SSO, role-based access control (RBAC), least privilege, and connector approvals directly into the platform fabric as code (Policy-as-Code).
- Lead Maintenance & Runbook Engineering: Lead platform maintenance activities including configuration updates, version management, vendor coordination, and renewal support. Create and maintain robust runbooks, support guides, and handoff documentation.
- Serve as an Operational Escalation Point: Partner closely with Security, IT, Legal, and business teams to resolve user issues and operational blockers, aligning tooling with acceptable use policies and data handling rules.
- Build the AI platform. Help create a greenfield AI platform and the lifecycle around it so teams can use AI in a safe and consistent way. Define the standards and guardrails for how AI systems are built, governed, deployed, monitored, rolled back, and shut down when needed.
- Strengthen AWS infrastructure. Design, secure, and scale AWS infrastructure for AI systems and platforms. Bring strong experience with Bedrock, IAM, security, network security, private connectivity, egress controls, and policy-based access to services and tools.
- Drive Architectural Alignment via Technical Reviews: Facilitate collaborative design reviews to define and socialize AI architectural standards across the organization. Use this process to codify best practices and ensure that "paved path" solutions are practical, vetted, and widely adopted by engineering teams.
- Lead Cross-Departmental Technical Partnerships: Act as a central technical stakeholder, proactively partnering with engineering departments to validate requirements, unify solution architectures, and ensure platform standards align with real-world engineering needs, effectively reducing fragmentation and "Shadow AI."
What You'll Bring:
- 5+ years of Software, Platform, or Systems Administration experience: A proven track record administering or supporting enterprise AI tools, developer tooling, or SaaS platforms with a strong focus on access management, support, and maintenance.
- Hands-on Familiarity with the AI Stack: Experience configuring, deploying, or building systems that leverage agentic architectures, tool-calling, and platforms like Glean, Gemini, Devin, Claude, and Portkey.
- Identity & Governance Expertise: Strong understanding of SSO, RBAC, least privilege, identity lifecycle management, secure data handling, and secure connector governance in an enterprise environment.
- Solid Engineering & Infrastructure Fundamentals: Proficiency in modern backend languages (Python, Go, TypeScript) and technical integrations alongside observability, monitoring, incident alerting, and service reliability practices.
- PDLC Rigor: A strong engineering philosophy rooted in documentation, change management, configuration management, and support processes for production-grade systems.
- Service-Oriented Mindset: The ability to translate technical constraints into practical guidance for both technical and non-technical users, helping teams adopt new tools safely and sustainably.
How Success is Measured in Year 1:
- Governed & Scalable AI Paved Path: Core AI platforms have clear, scalable access and support processes with strong license hygiene, documented ownership, and automated provisioning flows.
- Robust Gateway Foundation: Portkey or the approved gateway layer is operating as a trusted, highly available foundation for centralized model access, guardrails, and real-time observability.
- Operational Rigor & Support: Automated evaluation and testing frameworks are introduced, and solution teams can rely on stable paved-path platforms, documented runbooks, and active technical support channels.
- Stack Rationalization & Visibility: Leadership has precise visibility into tool adoption, usage trends, costs, risks, and reliability through recurring reporting and centralized metrics.
How We Work
We balance creativity and innovation on a foundation of in-person collaboration. For most roles, our employees work three or more days in our offices, where they have the opportunity to collaborate in-person, adding richness to our culture and knitting us closer together.
How We Reward You
Realtor.com is committed to investing in the health and wellbeing of our employees and their families. Our benefits programs include, but are not limited to:
- Inclusive and Competitive medical, Rx, dental, and vision coverage
- Family forming benefits
- 13 Paid Holidays
- Flexible Time Off
- 8 hours of paid Volunteer Time off
- Immediate eligibility into Company 401(k) plan with 3.5% company match
- Tuition Reimbursement program for degreed and non-degreed programs
- 1:1 personalized Financial Planning Sessions
- Student Debt Retirement Savings Match program
- Free snacks and refreshments in each office location
