RL Environments Engineer — Build Deterministic Agent Sandboxes

Labelbox is seeking a Forward Deployed Engineer to design, develop, and operationalize reinforcement learning environments. You’ll build sandboxed, reproducible environments that AI agents interact with during training and evaluation, delivering robust, observable infrastructure for team use.

You’ll write production-grade infrastructure code and integrate with open-source RL tooling, collaborating with data operations to ensure environments are reliable for human annotators and model agents