RL Data Engineer - Design Training Tasks for Coding Agents

Anysphere; San Francisco, Northern (CA, KY); Hybrid; USD 130,000 - 180,000; Full time

Job summary

Anysphere is seeking a Software Engineer, Reinforcement Learning to join our RL Data team and help design tasks, rewards, and environments that train coding agents. You will influence how we measure progress, curate data, and push the boundaries of what our models can learn.

You will iterate on traces and failure modes, turning insights into reusable pipelines and environments for multiple teams across the company.

Qualifications

• You write careful, fast code and have strong software engineering fundamentals.
• You like setting tasks: breaking a fuzzy capability into something concrete you can measure.
• You have an infra, data, or distributed systems background. RL experience is a plus, not a requirement.
• You enjoy looking at messy real-world agent behavior and turning it into a dataset or a tool.

Responsibilities

• Designing a task set that teaches a specific agent capability, then iterating on it from traces and evals until the model actually gets better.
• Reading a pile of agent traces, finding a failure mode or a surprising behavior, and building a system that surfaces more of the same.
• Turning a one-off recipe into something other teams can reuse: better rewards, cleaner environments, tighter data quality.
• Partnering with research on whether a dataset is actually teaching the thing we think it is.

Job description

Anysphere is seeking a Software Engineer, Reinforcement Learning to join our RL Data team and help design tasks, rewards, and environments that train coding agents. You will influence how we measure progress, curate data, and push the boundaries of what our models can learn.

You will iterate on traces and failure modes, turning insights into reusable pipelines and environments for multiple teams across the company.