Principal Agentic AI Engineer

Zoom Video Communications
Seattle
Workplace: OnsiteFull timeUSD 206,600 - 451,800 annuallyFunction: Data Science & Machine LearningSkills: ["Communication","Collaboration","Ownership mindset"]

Develop and scale an AI agent system framework by building the “agent harness” (runtime, orchestration, tool integration, memory, and evaluation layers). Partner with product teams to embed ZoomMate agent capabilities with minimal integration effort, including MCP-style connectors and agent-to-agent patterns across Zoom’s ecosystem. Design and run rigorous benchmarks for agent quality and reliability, and own the full lifecycle from architecture through deployment and monitoring at Zoom scale.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Zoom Video Communications
Zoom Video Communications
1 day ago

Principal Agentic AI Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 22 hours agoStatus: Live

Job Summary

Develop and scale an AI agent system framework by building the “agent harness” (runtime, orchestration, tool integration, memory, and evaluation layers). Partner with product teams to embed ZoomMate agent capabilities with minimal integration effort, including MCP-style connectors and agent-to-agent patterns across Zoom’s ecosystem. Design and run rigorous benchmarks for agent quality and reliability, and own the full lifecycle from architecture through deployment and monitoring at Zoom scale.
Location: Seattle
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Sr. Manager level

Key Responsibilities

  • •Design, build, and improve the ZoomMate agent harness including orchestration, tool use, sandboxing, memory management, context handling, and multi-step reasoning loops.
  • •Architect the agent framework and API/SDK surface so product teams can embed capabilities with minimal integration cost.
  • •Build and integrate tool-use and interoperability layers, including MCP-style connectors and agent-to-agent patterns across Zoom and third-party apps.
  • •Design and run evaluations and benchmarks for agent quality (reasoning, tool-use success, latency, and cost) and use results to drive iteration.
  • •Own the end-to-end lifecycle of services you build, including design docs, code review, deployment, monitoring, and on-call support.

Pay and Benefits

Salary: USD 206,600 - 451,800 annually

Key Requirements

  • •5+ years of experience building production software and/or ML systems.
  • •Practical experience building agentic systems with LLMs (tool use, planning, reasoning, memory, orchestration, or multi-agent coordination) in production or prototype formats.
  • •Strong programming fundamentals including data structures, algorithms, concurrency, and system design.
  • •Proficiency in Python, and comfort with at least one of Java, Go, or TypeScript depending on the surface.
  • •Experience with agent frameworks/orchestration (LangGraph, LangChain, AutoGen, or equivalent) and RAG/vector databases; plus LLM post-training (fine-tuning), reinforcement learning, or agent evaluation frameworks.
Experience:Machine learningLLMsAgentic systemsProduction software
Skills:CommunicationCollaborationOwnership mindset
Tech Stack:PythonJavaGoTypeScriptClaude CodeCodexLangGraphLangChainAutoGenRAGVector databasesMCP-style connectorsAgent-to-agent (A2A)ChatKitAPI/SDKMulti-step reasoning

Company Brief

Zoom Video Communications
Provides video conferencing, chat, phone, webinar, and collaboration software for businesses, schools, and individuals. Its platform is widely used for remote meetings, virtual events, and hybrid work communication.
Industry: SaaS
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Public Company
Valuation: Public Company (Market Cap in USD)
Funding: IPO / Publicly Listed
Headquarters: San Jose, United States
Founded: 2011
WebsiteLinkedIn