Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Gemini, Cursor and Grok
Connect

Anysphere, Inc. (doing business as Cursor)

Software Engineer RL Environments

Posted Updated
Discussion

Description

You will build platforms that create realistic reinforcement-learning environments at scale. You will turn raw data into training-ready environments, apply quality standards, create self-service APIs and tooling, and translate model-capability goals into effective tasks and experiments.

Responsibilities

  • Build platforms for complex and diverse reinforcement-learning environments at scale
  • Design factories that turn raw data into realistic environments
  • Define and apply quality standards across training data sources
  • Create self-service APIs and tooling for task and environment development
  • Translate model-capability goals into effective training tasks and environments

Requirements

  • Strong software engineering fundamentals
  • Experience with data platforms, developer tools, distributed systems, or ML infrastructure
  • Ability to turn quality standards into automated checks
  • Experience building pipelines from heterogeneous data
  • Knowledge of model behavior and capability evaluation

Skills

Apply

See also

Software Engineering jobs by country — openings, pay and top skills →