Principal Machine Learning Engineer (Memory & Context)

About the teamThe Agentic AI team at Zillow is at the forefront of transforming the real estate industry by helping millions of people use AI assistants to find their next home.

• About the team
• The Agentic AI team at Zillow is at the forefront of transforming the real estate industry by helping millions of people use AI assistants to find their next home. We aim to redefine the home shopping and transaction experience by providing an always-on assistant that integrates personalized user insights with Zillow's knowledge. Within this organization, our team owns how the assistant remembers and understands each user across a home search that can last for months: agent memory, context engineering, and the evaluation of agents running in production. We are a senior, fast-moving team of machine learning engineers who do the science and own taking it to production. About the role
• As a Principal Machine Learning Engineer on the Agentic AI team, you will get to:
• Own the architecture of agent memory: what Zillow's assistant remembers about each user across conversations, and how memories are written, retrieved, updated, and retired
• Lead context engineering for production agents: assembling, prioritizing, and compressing context from conversation history, user memory, tools, and skills so every response is relevant, fast, and cost-efficient
• Build and orchestrate agents end to end, from prompt and context design to deployment and operation in production
• Define evaluation frameworks for memory and context quality, offline and online, and use them to drive product and technical decisions
• Stay on the cutting edge of emerging agentic paradigms, including memory architectures and long-context techniques, and convert them into tangible product innovation
• Lead complex, multi-team initiatives and communicate technical direction clearly to engineers, partner teams, and leadership
• 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 $209,400.00 - $334,600.00 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 $199,000.00 - $317,800.00 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. Who you are
• You are a hands-on technical leader with high agency: when a problem is ambiguous or blocked, you go talk to the people who can solve it, and you make your work visible.
• Must-haves
• A master's degree or above, or equivalent experience, in Computer Science, Electrical Engineering, or a related field
• 5+ years of experience deploying large-scale ML systems, including at least the most recent year building and shipping LLM-based agents in production
• Hands-on experience building agents end to end: orchestration, prompt engineering and optimization, and context engineering
• Experience evaluating agentic systems and using those results to improve them
• Proven technical leadership: you have influenced technical direction across teams and mentored other engineers
• Strong communication skills, including presenting to senior leadership
• Strong programming skills in Python and familiarity with agentic AI frameworks such as LangGraph, Agents SDK, or AutoGen
• Nice-to-haves
• Experience designing agent or user memory systems (long-te