Agent Reliability Engineer, GTM

Role Overview

As an Agent Reliability Engineer, you’ll own the health, cost, performance, and business impact of the GTM Agent, and build the feedback loops that keep it improving. You’ll work across multiple technologies, including Python, FastAPI, LangGraph, and OpenAI models.

What You Will Do

Your day-to-day responsibilities will include monitoring production health, triaging issues, running eval suites, tracking cost and latency, and building business metrics to show leadership what the agent is worth.

Why It Might Be a Fit

We’re looking for someone with strong production Python and SQL skills, experience running LLM applications, and SRE or production operations instincts. You should be comfortable working in traces, logs, and warehouse tables, and have a healthy skepticism about metrics.

Requirements

• Strong production Python and SQL skills
• Real experience running LLM applications
• SRE or production operations instincts

Benefits

• Medical, dental, and vision coverage
• Flexible vacation
• 401(k) plan
• Meals on in-office days