Principal Machine Learning Engineer (Memory & Context)
About The Position
The Principal Machine Learning Engineer will join Zillow’s Agentic AI team, which develops AI assistants to help people find homes. The team is responsible for how the assistant remembers and understands users over home searches that may span months, including agent memory, context engineering, and evaluating agents in production. This role owns the architecture of agent memory, including how user memories are written, retrieved, updated, and retired. It leads context engineering for production agents by assembling, prioritizing, and compressing information from conversation history, user memory, tools, and skills to make responses relevant, fast, and cost-efficient. The role builds and orchestrates agents end to end, from prompt and context design through deployment and production operation; defines offline and online evaluation frameworks for memory and context quality; and applies emerging agentic approaches to product innovation. The position also leads complex, multi-team initiatives and communicates technical direction to engineers, partner teams, and leadership. Zillow categorizes this as a remote position. Remote employees work from a physical location of their choice that must be identified to the company; U.S. employees may live in any of the 50 states, with limited exceptions. The position offers a location-dependent base salary range and is eligible for equity awards.
Requirements
- A master’s degree or above, or equivalent experience, in Computer Science, Electrical Engineering, or a related field.
- At least 5 years of experience deploying large-scale machine learning systems, including at least the most recent year building and shipping LLM-based agents in production.
- Hands-on experience building agents end to end, including orchestration, prompt engineering and optimization, and context engineering.
- Experience evaluating agentic systems and using evaluation results to improve them.
- Proven technical leadership, including influencing technical direction across teams and mentoring engineers.
- Strong communication skills, including the ability to present to senior leadership.
- Strong Python programming skills.
- Familiarity with agentic AI frameworks such as LangGraph, Agents SDK, or AutoGen.
Nice To Haves
- Experience designing agent or user memory systems, including long-term, episodic, or user-profile memory.
- Experience with dialogue systems that sustain long, multi-session conversations.
- Experience personalizing AI assistants using conversation history.
- Publications, patents, or open-source contributions related to memory, long-context models, or agents.
Responsibilities
- Own the architecture of agent memory, including how memories are written, retrieved, updated, and retired.
- Lead context engineering for production agents by assembling, prioritizing, and compressing conversation history, user memory, tools, and skills.
- Build and orchestrate agents end to end, from prompt and context design to deployment and production operation.
- Define offline and online evaluation frameworks for memory and context quality and use results to guide product and technical decisions.
- Track emerging agentic paradigms, including memory architectures and long-context techniques, and convert them into product innovation.
- Lead complex, multi-team initiatives and communicate technical direction to engineers, partner teams, and leadership.
- Mentor other engineers and influence technical direction across teams.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Principal
