Idler builds reinforcement learning environments that teach AI models to code like 0.01% engineers. The Staff Software Engineer will design and build scalable systems for generating reinforcement learning environments and create automated QA systems to validate their quality and fairness.
Responsibilities:
- Design and build scaleable systems that generate RL environments
- Create automated QA systems to validate environment quality and fairness
- Work directly with AI researchers at leading labs to understand what makes training data effective
- Support new product lines as we expand beyond coding environments
- Lead the process of identifying, specifying, and implementing core technology primitives that maximize the leverage of the rest of the team
- Understand and own the technology stack end-to-end
- Lead and mentor more junior members of the team