RL Environments Architect

As an RL Environments Architect, you’ll design, instrument, and govern the simulated worlds where agents learn — from compact task microcosms to multi-agent, tool-using ecosystems. You’ll define the primitives, reward structures, interfaces, and telemetry that let us stress-test emerging capabilities while keeping training signals faithful, stable, and scalable.

Not only will you build environments, you’ll craft standards for data quality and reproducibility across large-scale agent gyms. This is a role for someone who sweats the details of simulation fidelity, thinks in terms of coverage and failure surfaces, and loves turning messy real-world phenomena into learnable curricula. Your work will form the backbone for safe, rapid progress in agentic systems.

• Architect a modular environment framework with clear APIs, curriculum scaffolds, and configurable reward/termination schemas