Principal Product Manager, Agent Platform

Toast Toast · Enterprise · United States · Remote · R & D : Product : Customer Experience Platform

Principal Product Manager for Toast's Agent Platform, defining and scaling the foundational layer for AI agents across the company. This role focuses on orchestration, tool integration, governance, evaluation, and observability to ensure a seamless and trustworthy AI experience for Toast IQ.

What you'd actually do

  1. Define the long-term vision and roadmap for the Agent Platform, the shared orchestration and tooling layer for all Toast agents
  2. Build the platform capabilities that enable agent-to-agent collaboration, subagent routing (A2A), shared memory, and unified voice/tone
  3. Establish standards and systems for MCP tool development, entitlement controls, and tool orchestration
  4. Own evaluation, observability, and monitoring frameworks, including instrumentation, tracing, eval pipelines, and production quality standards
  5. Enable teams across Toast to easily build and integrate agents

Skills

Required

  • 8+ years of product management experience, including significant ownership of technical platform or infrastructure products
  • Deep familiarity with LLM systems, agent architectures, tool calling patterns, or AI evaluation frameworks
  • Strong technical fluency: comfortable discussing APIs, orchestration layers, memory systems, protocols (e.g., A2A/MCP), and observability tooling
  • Experience building developer-facing platforms or enablement systems used by multiple teams
  • Proven ability to define, and own, quality standards and operationalize monitoring for complex systems in production
  • Strong systems thinking and ability to balance short-term enablement with long-term architectural integrity

Nice to have

  • Embrace and advocate for the use of AI tools to accelerate product discovery, streamline execution, and explore new product experiences - helping shape how we build and what we build.

What the JD emphasized

  • Deep familiarity with LLM systems, agent architectures, tool calling patterns, or AI evaluation frameworks
  • Proven ability to define, and own, quality standards and operationalize monitoring for complex systems in production

Other signals

  • platform
  • agent orchestration
  • tool integration
  • governance
  • evaluation
  • observability