Online & async RL infrastructure

The algorithm is maybe a tenth of the work. The rest is infrastructure: sandboxes that run hundreds of thousands of agent rollouts, a pipeline that keeps the training accelerators saturated and the discipline to learn from live traffic without breaking it.

This role explicitly includes building the eval harnesses, sandboxed environments and async RL pipelines that research needs. The interview - especially the paid practical onsite - rewards reasoning about throughput, staleness and safety as concretely as about advantages.