Agentic AI Engineer

Zoom • Seattle, WA

1d • $177,100 - $387,500 • Hybrid

About The Position

This role is part of Zoommate's agent mission and is responsible for building the shared agent harness—including runtime, orchestration, tool use, memory, and evaluation layers—that downstream agent products depend on. The engineer will shape infrastructure used across Zoom product teams and work hands-on from design through production. The role is part of a lean, high-engineering-density team with short decision paths and end-to-end ownership, working across agent infrastructure, applied research, and product integration.

The position is hybrid and requires on-site presence four days per week at Zoom's Seattle, Washington office. Remote arrangements are not available. The role owns the full lifecycle of services, including design documentation, code review, deployment, monitoring, and on-call, and collaborates with product teams to turn integration challenges into shared infrastructure improvements.

Requirements

• At least 5 years of industry experience building production software and/or ML systems.
• Hands-on experience delivering agentic systems using LLMs, including areas such as tool use, planning and reasoning, memory, orchestration, or multi-agent coordination.
• Strong programming fundamentals across data structures, algorithms, concurrency, and system design.
• Fluency in Python and comfort with at least one of Java, Go, or TypeScript.
• At least 2 years of API/SDK development experience (REST, gRPC, or similar), with demonstrated ability to design infrastructure used by other teams.
• Excellent communication skills, a collaborative and ownership-driven mindset, and ability to translate integration pain points into shared infrastructure improvements.

Nice To Haves

• Experience with agent frameworks and orchestration tools such as LangGraph, LangChain, AutoGen, or equivalent.
• Experience with RAG pipelines or vector databases.
• Experience with LLM post-training/fine-tuning, reinforcement learning, or building rigorous agent evaluation frameworks.
• Familiarity with large-scale engineering platforms and their tooling.

Responsibilities

• Design, build, and evolve the Zoommate agent harness, including orchestration, tool invocation, sandboxing, memory and state management, context management, and multi-step reasoning loops.
• Architect the underlying agent framework and API/SDK surface so Zoom product teams can embed Zoommate Agent capabilities with minimal integration cost.
• Build and integrate tool-use and interoperability layers, including MCP-style connectors and agent-to-agent patterns, enabling agents to operate across Zoom's ecosystem and third-party apps.
• Design and run evaluations and benchmarks for agent quality across reasoning, tool-use success, latency, and cost, and use findings to drive continuous iteration.
• Own the full lifecycle of services, including design docs, code review, deployment, monitoring, and on-call, with production-grade reliability at Zoom scale.
• Partner with product teams to turn real integration pain points into better shared infrastructure rather than one-off fixes.
• Integrate with Zoom's engineering platforms and leverage internal tooling to accelerate delivery.
• Apply AI coding agents as first-class teammates in daily work and use that experience to inform the design of tools for agents.

Benefits

• Benefits program offers perks, benefits, and options intended to support physical, mental, emotional, and financial health, work-life balance, and community involvement.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed