Principal Agentic AI Engineer
$206,600–$206,600 year
HybridSeattle, Washington, United States
Job Summary
Design and improve the ZoomMate agent harness, covering orchestration, tool use, sandboxing, memory management, and multi-step reasoning loops. Architect the underlying framework and API/SDK surface to enable seamless embedding of agent capabilities across Zoom's ecosystem. Build interoperability layers including MCP-style connectors and agent-to-agent patterns, while designing evaluations for reasoning, tool-use success, latency, and cost. Own the full lifecycle from design docs to production monitoring and on-call rotation. Partner with product teams to transform integration pain points into shared infrastructure.
Required Qualifications
- 5+ years of industry experience building production software and/or ML systems
- Show practical experience developing agentic systems using LLMs, including tool use, planning, reasoning, memory, orchestration, or multi-agent coordination, implemented in production or research/prototype formats
- Possess programming fundamentals: data structures, algorithms, concurrency, and system design
- Demonstrate be fluent in Python
- Have experience with agent frameworks and orchestration (LangGraph, LangChain, AutoGen, or an equivalent), RAG pipelines, or vector databases
- Possess experience with LLM post-training/fine-tuning, reinforcement learning, or building rigorous agent evaluation frameworks
Desired Qualifications
- comfortable with at least one of Java/Go/TypeScript depending on the surface you're building
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.