AI Provider Operations & Support Engineer

Role overview Own the technical process for bringing AI models and inference providers onto a multi-model platform. The work combines building internal tools and evaluations with coordinating integrations, quality checks, and releases across a range of model types.

Responsibilities - Develop tools that make provider onboarding faster and model endpoints easier to assess. - Create evaluations to compare model and endpoint behavior, including quality and latency. - Document operational workflows and identify steps that can be automated. - Plan launches for models such as text, audio, image, video, embedding, and reranking systems, including tests, pricing and quota checks, and documentation. - Coordinate integration, quality assurance, and release timing with providers. - Maintain version information and release notes, and manage migrations and deprecations.

Requirements - Around two to three years of experience in software engineering, product operations, a startup, or a related role. - Ability to work with inference APIs, read technical documentation, and troubleshoot using logs and tools such as cURL or Postman. - Experience with TypeScript or JavaScript, and/or Python. - Ownership, curiosity, quick learning, and a willingness to ship improvements promptly. - Interest in AI and developer experience. - A computer science or engineering degree is useful but not required if technical ability is demonstrated.

Benefits and work setup - Exposure to real-world use of large language models and access to emerging models. - Opportunity to grow into a specialized or senior role. - Collaborative, high-ownership team environment. - Compensation, benefits, and equity are offered; details are not specified.