Skip to main content

OpenRouter

Provider Operations & Support Engineer

Remote (US) (Remote)fulltimemidAdded today

About this role

OpenRouter seeks an operations-focused engineer to manage AI model launches and provider onboarding at their LLM marketplace. You'll orchestrate end-to-end launches while building internal tooling and benchmarks to streamline the integration process for new models and providers.

What you'll do

  • Execute full model launch cycles including scoping, testing, performance validation, pricing, and documentation
  • Coordinate with model providers on integration, quality assurance, and release timelines
  • Manage versioning, release notes, deprecations, and customer migrations
  • Build internal tools and scripts to accelerate model onboarding workflows
  • Develop evaluation frameworks to assess model quality and endpoint performance
  • Document and automate internal processes for scaling operations

What they're looking for

  • TypeScript or JavaScript
  • Python
  • API integration and troubleshooting
  • Git version control
  • REST API fundamentals
  • LangChain or LlamaIndex (bonus)
  • Cloud platforms or observability tools (bonus)
  • Technical writing and documentation

Benefits

  • Remote work (US-based)
  • Access to frontier AI models and real-world adoption insights
  • Growth opportunities into specialized or senior engineering roles
  • Competitive compensation with equity
  • High-ownership collaborative environment
Apply with Autofill

Opens the application — the Jobs AI extension fills it for you. Set up autofill

Opens the official application on the employer’s site. No login required.

OpenRouter

OpenRouter builds a platform that routes and manages high-volume requests across language models and AI inference services. The company is hiring software engineers for platform infrastructure and product development, as well as forward-deployed engineers to support customer implementation and scaling.

View all jobs at OpenRouter

Likely interview questions

  • Walk us through how you'd approach launching a new model end-to-end—what phases matter most and what could go wrong?
  • Describe a time you debugged an API integration issue using logs or tools like Postman. How did you troubleshoot it?