Principal Machine Learning Engineer, Agentic AI

Zillow Zillow · Consumer · United States · Remote

Principal Machine Learning Engineer on the Agentic AI team to develop large-scale, fault-tolerant multimodal agentic experiences, design agent interaction modes (Voice AI, Deep Research), pioneer evaluation frameworks, tracing systems, and safety guardrails, and lead multi-team initiatives bridging research and engineering.

What you'd actually do

  1. Develop large-scale, fault-tolerant multimodal agentic experiences that reach millions of customers
  2. Design and develop multiple agent interaction modes, including Voice AI and Deep Research.
  3. Pioneer robust evaluation frameworks, tracing systems, and safety guardrails to ensure our highly-visible AI agents remain trustworthy and responsible
  4. Remain on the cutting edge of emerging agentic paradigms and convert them into tangible product innovation
  5. Lead complex, multi-team initiatives, bridging the gap between applied research and highly scalable engineering

Skills

Required

  • Master's degree or above, or equivalent experience in Computer Science, Electrical Engineering, or a related field
  • 5+ years of experience with a proven track record of deploying large-scale ML models
  • 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

Nice to have

  • A track record of writing articles, patents, and publishing high-impact research is a strong plus

What the JD emphasized

  • building products using frontier multimodal LLMs
  • deploying large-scale ML models
  • building agent-based systems, multi-agent collaboration, or similar paradigms
  • building AI services capable of handling hundreds of millions of daily interactions with high availability, low latency, and robust fault tolerance

Other signals

  • Develop large-scale, fault-tolerant multimodal agentic experiences
  • Design and develop multiple agent interaction modes, including Voice AI and Deep Research
  • Pioneer robust evaluation frameworks, tracing systems, and safety guardrails
  • Lead complex, multi-team initiatives, bridging the gap between applied research and highly scalable engineering