RL Environments Architect

The Role

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.

What You'll Do

• Architect a modular environment framework with clear APIs, curriculum scaffolds, and configurable reward/termination schemas
• Establish quality bars: coverage metrics, invariance checks, and trace audits for environment outputs and agent experience buffers
• Instrument rich telemetry for episode rollouts; mitigating reward hacking, mode collapse, and exploitable loopholes
• Partner with researchers to translate real-world tasks into robust simulations, including synthetic data generators and evaluation suites

What We’re Looking for

• Simulation & Systems Depth - Experience building RL environments or simulators (e.g., custom physics, multi-agent, tool APIs) with an eye for determinism, performance, and observability
• Data Quality Leadership - Strong instincts for designing reward functions, scenario taxonomies, and QA pipelines that keep signals aligned and drift-free
• Builder’s Mindset - Comfort collaborating across research and engineering to ship pragmatic, testable environments that evolve with model capabilities