AI Provider Operations & Support Engineer

The role

This person will own model launches and provider onboarding. They will build internal tools for benchmarks and operations and run launch playbooks for various model types.

What you will do

• Build internal tools to help speed up the model onboarding process
• Build internal evals to quickly evaluate models and endpoints
• Document internal processes and prime them for automation
• Run end-to-end launch playbooks for various model types
• Coordinate with model providers to integrate, QA, and hit ship dates
• Maintain clear versioning and release notes
• Manage deprecations and migrations

Required qualifications

• 2-3 years at a startup, software engineering, product ops, or similar
• Comfortable building with inference APIs, including Chat Completions, Responses, and/or Messages API
• Can read API docs and troubleshoot with logs/cURL/Postman
• Experience with TypeScript/JavaScript and/or Python

Nice to have

• CS/Engineering degree

Benefits

• A front-row seat to real-world LLM adoption and access to cutting-edge models
• Growth into specialized or senior roles as we scale
• Collaborative, high-ownership environment
• Competitive compensation, benefits, and equity

About the company

OpenRouter is the open AI routing and infrastructure layer that enterprises use to access, manage, and optimize the best large language models across providers. It powers advanced AI teams by providing flexibility to move fast and scale.