AI Provider Operations & Support Engineer

AI model gateway and marketplace offering a unified API to access, route, and manage models from multiple providers.

Distributed
About OpenRouter

OpenRouter provides developers and businesses with a single, OpenAI-compatible API for hundreds of AI models. It supports provider failover, routing for price, latency and reliability, plus enterprise controls and observability.

View jobs by OpenRouter

Skills

Candidate Availability

Required and preferred rules are kept separate and reflect the wording in the original posting.

About the Role

You will build internal tools and evaluations that accelerate model onboarding. You will run model-launch playbooks, coordinate provider integrations and quality assurance, manage versioning and migrations, and document processes for automation.

Requirements

  • 2–3 years of experience at a startup, in software engineering, product operations, or a similar role
  • Ability to build with inference APIs, including Chat Completions, Responses, or Messages APIs
  • Ability to read API documentation and troubleshoot with logs, cURL, or Postman
  • Experience with TypeScript, JavaScript, or Python
  • Technical aptitude

Responsibilities

  • Build internal tools to speed up model onboarding
  • Build internal evaluations for models and endpoints
  • Document internal processes for automation
  • Run end-to-end model launch playbooks
  • Coordinate provider integrations, quality assurance, and launch dates
  • Maintain versioning and release notes
  • Manage deprecations and migrations

Benefits

  • Equity
AI Provider Operations & Support Engineer at OpenRouter | JobStash