Sr. AI Architect; DFW Area

Sr. AI Architect (DFW Area)

Join to apply for the Sr. AI Architect (DFW Area) role at Real Page, Inc.

Real Page is at the forefront of the Generative AI revolution, dedicated to shaping the future of artificial intelligence within the Property Tech domain. Our Agentic AI team is focused on driving innovation by building next generation AI applications and enhancing existing systems with Generative AI capabilities.

We are seeking a Sr. AI Architect who is a senior technical leader who provides end-to-end technical direction for our Agentic & Generative AI ecosystem across the Real Page platform. You will define the reference architectures, patterns, and guardrails that enable teams to safely and efficiently build AI-powered products in the Prop Tech domain.

You will work at the intersection of AI, data, and platform engineering—shaping how we use LLMs, RAG, agentic frameworks, and emerging multimodal capabilities ’ll partner with product and engineering leadership to translate business strategy into an AI architecture roadmap, enabling multiple delivery teams to build on a coherent, secure, and observable AI platform.

This team has been coming to our HQ one week out of the month - it will be expected that you will travel to the corporate HQ from time to time.

• Enterprise AI Architecture & Strategy
• Define the overarching AI architecture for Real Page:
  • Standard patterns for RAG, multi-agent systems, and workflow orchestration
  • Integration with existing microservices, data platforms, and event-driven systems.
• Create and own AI reference architectures, blueprints, and design patterns that individual product teams can adopt and extend.
• Evaluate and recommend vendors and technologies across:
  • Model providers (OpenAI, Anthropic, Google, xAI, Meta, Mistral, etc.)
  • Vector databases (pgvector, Pinecone, Weaviate, Qdrant, etc.)
  • Agent frameworks and orchestration tools (Agents SDK, Google ADK, Lang Chain, workflow engines like n8n, Zapier, etc.)
• Platformization & Shared Capabilities
• Own the end-to-end architecture for AI products and platforms:
  • Model selection strategy (Google vs. OpenAI, small vs. large models)
  • Multi‑agent and workflow orchestration patterns (responder/thinker pattern, tool calling, agentic frameworks)
  • Data and retrieval architecture (RAG, hybrid search, knowledge graphs, semantic caching)
• Define and champion approaches for:
  • Semantic caching, cost optimization, and latency reduction
  • Multi‑tenant, domain‑isolated AI use across Real Page products.
• Data, Retrieval & Knowledge Architecture
• Partner with Data/Analytics teams to align AI architecture with data strategy:
  • Data sourcing from warehouses/lakes, operational databases, event streams.
  • Governance for which data can be used in training, retrieval, and inference.
• Architect robust RAG and knowledge systems:
  • Taxonomies and metadata standards
  • Implement knowledge retrieval process that draws from multiple sources and uses reranking to improve the response quality.
  • Long‑context models, memory systems, and potential use of knowledge graphs / vector‑native databases.
• Define ingestion and refresh strategies to keep AI knowledge current and trustworthy.
• Security, Compliance & Responsible AI
• Define architectural guardrails for:
  • Data privacy, PII redaction, and tenant isolation
  • Encryption, key management, and secure connectivity to model providers
  • On‑prem / VPC deployments for sensitive workloads where required.
• Collaborate with Security, Privacy, and Legal teams to define policies and patterns for:
  • Content safety, toxicity filtering, and jailbreak resistance
  • Auditability and traceability of AI decisions (logs, traces, model versions, prompts, and responses).
• Establish a Responsible AI framework in partnership with leadership:
  • Guidelines for fairness, bias mitigation, and explainability where appropriate
  • Review processes for high‑risk AI features.
• Observability, Evaluation & MLOps
• Architect end‑to‑end observability for AI systems:
  • Traces and spans for prompts, model calls, tool calls, and RAG steps (e.g., Open Telemetry, Lang Smith).
  • Metrics for latency, cost, error rates, and model‑specific KPIs.
• Define standard evaluation approaches:
  • Offline evaluation harnesses for RAG…