Build the endpoint production AI teams stop worrying about.
Direct Inference makes model selection, capability handling, spend guardrails, and provider churn disappear behind one durable surface. We are hiring people who like hard infrastructure, crisp product taste, and systems that earn trust by holding less.
Work directly with high-intent customers to get production AI workloads running on Direct Inference, then bring the sharp edges back into the product and serving engine.
Embed with customers during pilots, migrations, and launch moments so one endpoint replaces brittle model-selection code.
Build reference integrations, workflow-specific tooling, and small product fixes that turn deployment friction into reusable platform improvements.
Partner with engineering on request classification, observability, spend controls, and reliability when a customer workload exposes a new edge case.
Translate customer patterns into docs, examples, product requirements, and internal operating knowledge.
Build the product and platform surfaces that make Direct Inference feel like one dependable endpoint, from API workflows to dashboard tools used by production teams.
Craft fast, polished interfaces for Direct Inference, including the playground, traces, billing controls, documentation chrome, and developer-facing product flows.
Advance the systems that classify requests, evaluate answer quality, and keep code, reasoning, vision, document, and structured-output traffic served by the right capability.