RL Environments Architect
Surge AI · United States - Remote
CHECKED 20H AGO
Infrastructureremote
At a glance
Highlights
- Design and govern simulated worlds where AI agents learn and evolve.
- Define reward structures and telemetry to keep training signals stable.
- Build modular environment frameworks with curriculum scaffolds and audits.
Ideal candidate
Systems-minded builder obsessed with simulation fidelity and data quality who loves turning messy real-world tasks into robust, learnable curricula for agents.
Requirements
- Experience building RL environments or simulators with focus on determinism, performance and observability
- Strong instincts for designing reward functions, scenario taxonomies and QA pipelines that keep signals aligned
- Comfort collaborating across research and engineering to ship pragmatic, testable environments
Lab profile
About Surge AI
Human data platform powering frontier AI models to raise AGI with rich human intelligence.
What they build
- Human data labeling platform
- RLHF training data
- AI model evaluation
Known for
- Powers models for OpenAI, Anthropic, Google, Meta, Microsoft
- Expert human data across code, language and domains
Key facts
- Founded in 2016
- Headquartered in San Francisco, CA