Zillow is transforming the real estate industry through the Agentic AI team, which focuses on using AI assistants to enhance the home shopping experience. As a Principal Machine Learning Engineer, you will lead the development of multimodal AI experiences and ensure the reliability and innovation of AI agents.
Responsibilities:
- Develop large-scale, fault-tolerant multimodal agentic experiences that reach millions of customers
- Design and develop multiple agent interaction modes, including Voice AI and Deep Research
- Pioneer robust evaluation frameworks, tracing systems, and safety guardrails to ensure our highly-visible AI agents remain trustworthy and responsible
- Remain on the cutting edge of emerging agentic paradigms and convert them into tangible product innovation
- Lead complex, multi-team initiatives, bridging the gap between applied research and highly scalable engineering
- Distill complex research findings and AI system architectures into actionable insights for a diverse audience, including executives and cross-functional partner teams
Requirements:
- A master's degree or above, or equivalent experience in Computer Science, Electrical Engineering, or a related field, with emphasis on building products using frontier multimodal LLMs
- 5+ years of experience with a proven track record of deploying large-scale ML models, with the most recent 2-3 years building agent-based systems, multi-agent collaboration, or similar paradigms
- Experience developing engaging dialogue systems capable of long conversations, context-aware tool selection, and compliant response generation
- Experience building AI services capable of handling hundreds of millions of daily interactions with high availability, low latency, and robust fault tolerance
- Familiarity with various agentic AI frameworks, such as LangGraph, Agents SDK, AutoGen, and production ML infrastructure
- Strong communication skills, with the ability to influence technical direction across teams and present to executive leadership
- A track record of writing articles, patents, and publishing high-impact research is a strong plus