Most roles are based in New York, on-site.
Own the infrastructure layer of our inference cloud end-to-end: the control plane, the gateway in front of our ASIC fleet, and the observability stack. First infra hire, hands-on from day one.
Build the platform layer of our inference cloud — the OpenAI-compatible API surface, request path, streaming infrastructure, and benchmarking harnesses. Everything between an OpenRouter request and a token streaming back.
Run our $200M asset-backed equipment facility end-to-end — model, data room, lender process, term sheets, close — and own the capital stack from here.