Senior Fullstack Engineer, Mortgage Fulfillment AI

You'll join a close-knit engineering team in Zillow Home Loans Fulfillment who know our loan origination system in depth. Fulfillment covers the mortgage journey from application through funding. Today that work runs through human handoffs, third-party tools, and data spread across many systems. Our mission is to use AI agents to shorten that journey: fewer manual steps, faster condition clearing, and a loan process that keeps itself moving toward funding, bringing in a person only for the decisions that need one.

We value thoughtful technical leadership, rigor, and teamwork, and we're always looking for ways to raise the quality, reliability, and impact of what we build.

The Senior Software Development Engineer designs, builds, and operates production-grade agentic AI systems for mortgage Fulfillment. This role focuses on agentic AI, not general feature work, and centers on three areas: agent design and architecture, evaluation (evals) infrastructure, and the core infrastructure that runs agents. You'll own the architecture of your work streams from end to end, surface tradeoffs, and drive technical decisions on a problem with no existing playbook.

This is an individual contributor role.

You will get to Design and build multi-step AI agents that coordinate Fulfillment workflows such as document collection, condition clearing, and closing coordination, without requiring a person to step in at every step. Build evaluation frameworks that measure agent reliability, accuracy, and task completion, and use that signal to improve prompts, models, and fallbacks. This is essential for deploying AI safely in a regulated mortgage environment.

Architect and operate core agent infrastructure, including model serving, prompt pipelines, batching, queueing, and observability, designed for reliability: idempotency, retries, graceful degradation, and structured logging. Build robust integrations with third-party platforms such as Encompass and Docu Tech, working within their constraints and extension points to read state and write actions back reliably. Collaborate closely with Encompass administrators, Fulfillment operations, and Platform engineering partners to refine requirements, break down work, and deliver iteratively.

Set and advocate for engineering best practices in testing, measurement, observability, and incident response, and mentor other engineers through code reviews and design discussions.

This role has been categorized as a Remote position. Remote employees do not have a permanent corporate office workplace and, instead, work from a physical location of their choice, which must be identified to the Company. U.S. employees may live in any of the 50 United States, with limited exceptions. In California, Connecticut, Maryland, Massachusetts, New Jersey, New York, Washington state, and Washington DC the standard base pay range for this role is $ - $ annually.

This base pay range is specific to these locations and may not be applicable to other locations. In Colorado, Hawaii, Illinois, Maine, Minnesota, Nevada, Ohio, Rhode Island, Vermont, and Virginia the standard base pay range for this role is $ - $ annually. The base pay range is specific to these locations and may not be applicable to other locations.

In addition to a competitive base salary this position is also eligible for equity awards based on factors such as experience, performance and location. Actual amounts will vary depending on experience, performance and location. Employees in this role will not be paid below the salary threshold for exempt employees in the state where they reside.

• Bachelor's degree in Computer Science, Computer Engineering, or a related technical field, or an equivalent combination of education and experience.
• 8+ years of professional software engineering experience, including building and operating scalable, reliable services in a modern cloud environment.
• Proven experience owning an AI or ML system in production from end to end (designing, shipping, measuring, and iterating on it) with accountability for correctness, cost, and reliability.
• Hands-on experience in at least two of these areas: designing and running eval pipelines (including producing labeled data at scale); operating LLM or ML model serving and orchestrating multi-step AI workflows; building reliable integrations with third-party platforms and external APIs.
• Strong infrastructure instincts alongside AI fluency. You know agents often fail in…