AI Integration Architect

Role Summary

We are looking for a Senior AI Architect to design and deliver AI systems across Cotality’s property intelligence platform. This is a hands‑on individual contributor role that spans internal agentic systems powering property analytics and external AI integration architecture that enables Cotality’s data products to be consumable by AI agents, foundation model platforms, and enterprise developer ecosystems.

• Design and build agentic AI systems, including multi‑agent frameworks, orchestration layers, memory and retrieval architectures, and tool‑based reasoning pipelines that operate against structured and unstructured property data.
• Own the external AI integration architecture, API gateway configuration, MCP server patterns, authentication and authorization flows, tool schema standards, and the reference architecture that product teams follow to expose their APIs as agent‑consumable tools.
• Pioneer Agent Experience (AX) design as a first‑class methodology for the organization, ensuring APIs, tool descriptions, and data outputs are optimized for LLM comprehension, context limits, and deterministic reasoning.
• Establish and enforce technical standards for AI agents, focusing on tool description quality, input/output contracts, error handling patterns, and response metadata.
• Architect security and data provenance controls across the integration layer, including JWT claim schema design, defense‑in‑depth authorization patterns, audit logging, and response boundary enforcement.
• Design and implement observability and telemetry for AI systems to monitor token consumption, latency, error rates, prompt drift, LLM costs, and response quality in production.
• Establish CI/CD pipelines and evaluation frameworks for AI agents that measure accuracy, hallucination rates, and performance regressions before changes reach production.
• Optimize AI workload architecture by designing deployment strategies that decouple large model weights from application code, using optimized base images and dynamic runtime mounting.
• Scale inference and orchestration by architecting high‑throughput AI backends using specialized model servers such as vLLM or Triton on Kubernetes, with support for dynamic batching, streaming responses, and concurrent execution.
• Partner with platform engineering to build cost‑aware AI systems and design agentic workflows that handle cold‑start latencies, infrastructure scaling, and Spot instance evictions without dropping requests.
• Bring strong backend engineering practices to the AI layer, ensuring maintainable code in cloud or containerized environments.
• Lead reference architecture and MCP server build patterns that product teams use for exposing APIs as agent‑consumable tools.
• Collaborate closely with data engineers, product managers, and domain experts to produce accurate, traceable, and operationally meaningful AI outputs.
• Conduct architecture design reviews and maintain the technical quality bar as the organization’s AI portfolio expands.
• Create architecture decision records, technical standards, and reference documentation for engineering teams.

• 7 to 10 years of software engineering or architecture experience, strong background in API platforms and distributed systems, recent proven depth building LLM‑powered or agentic AI applications.
• Strong backend development background in Python, Java, or .NET, with expert understanding of object‑oriented design and distributed microservices.
• Proficiency in Python for agentic and tooling layers, or demonstrable ability to transition into Python.
• Hands‑on experience with agentic AI frameworks such as Lang Chain, Llama Index, or Auto Gen, with strong command of prompt engineering, context management, and tool integration.
• Solid foundation in API architecture and authentication patterns, including REST, OAuth
  2.0, JWT design, and API gateway technologies such as Apigee or Kong.
• Working knowledge of Agent Experience (AX) design principles, including context window constraints and tool description quality.
• Familiarity with AI observability tooling and monitoring of non‑deterministic LLM systems.
• Experience with CI/CD practices and…