Product Engineer (AI Agent Management)

Gravitee•Denver, CO

6d•$188,000•Hybrid

About The Position

We're looking for a Product Engineer to help build the core of how enterprises secure, govern, and control AI agents. This includes the Agent Gateway that governs agent-to-agent (A2A) communication, and the LLM control layer that gives enterprises centralized command over every LLM their agents call. You'll work close to customers and close to the code, owning a slice of the Agent Gateway or LLM control roadmap end to end. This is a role for someone who wants to own outcomes, not just tickets: you'll help decide what gets built, then build it.

Requirements

4+ years of software engineering experience, ideally in a product-facing or full-stack role.
Comfortable talking directly to customers and translating what you hear into a technical plan.
Hands-on experience with AI coding assistants (Cursor, Claude Code, GitHub Copilot or similar) as part of daily work.
Strong fundamentals in API design and distributed systems.
A bias toward shipping and iterating over building the theoretically perfect solution.

Nice To Haves

Familiarity with the A2A protocol or agent-to-agent communication patterns.
Experience with API gateways or API management platforms.
Exposure to LLM-based products or agentic workflows.
Experience integrating multiple LLM providers into a single product surface.
Experience with cost or usage governance for AI and LLM systems.
Familiarity with the Model Context Protocol (MCP) or similar orchestration standards.
Experience working in a fast-moving, ambiguous product environment.
Worked with APIs, cloud-native platforms, AI-enabled systems, or open source.

Responsibilities

Own a meaningful slice of the Agents or LLM control roadmap, from customer conversations through shipping and iterating on the result.
Build features for the Agent Gateway and A2A protocol support, or for multi-LLM routing, cost control, and reliability – depending on your pod – working closely with Product Management and Design.
Use AI-assisted development tools as a core part of your workflow to move faster from idea to shipped feature.
Dig into usage data and customer feedback to help decide what to build next, not just how to build it.
Prototype quickly, test with real users, and be willing to change course when something isn't landing.
Partner with Staff Engineers and other pods where the Agents surface touches LLM control, MCP, or the core API gateway – and vice versa.