Platform engineer at OpenRouter owning and evolving edge and cloud infrastructure (Cloudflare, Google Cloud, Vercel), scaling the data layer (Spanner, ClickHouse, Postgres), and optimizing performance, reliability, and cost for growing LLM inference traffic, while setting standards for tooling, observability, and on-call.
You will own and evolve edge and cloud infrastructure, operate the data layer, and improve performance for growing LLM traffic. You will partner on capacity, reliability, and cost, while establishing infrastructure tooling, observability, on-call practices, and operational patterns.
Responsibilities
Own and evolve edge and cloud infrastructure across Cloudflare, Google Cloud, and Vercel
Scale and operate Spanner, ClickHouse, and Postgres
Optimize performance for growing LLM inference traffic
Partner on routing-layer capacity, reliability, and cost
Set infrastructure and operations standards for tooling, observability, and on-call
Requirements
5+ years building and operating production infrastructure
Experience with GCP, AWS, or Azure
Experience with edge-first serverless platforms such as Cloudflare Workers
Expertise operating large-scale databases such as Postgres and Spanner