Remote Software Engineer, RL Data - Training Data Systems

Free resume; San Francisco (CA); Hybrid; USD 30,000 - 50,000; Full time

Job summary

SpaceXAI is hiring a Software Engineer for the RL Data team to shape training data and evaluation for agents. You will build environments that mimic production codebases and design graders to evaluate open-ended work, turning messy problems into scalable, verifiable data pipelines.

You’ll work on failing-proof data generation through automated checks and robust data production systems, with emphasis on reliability and reproducibility in a remote, full-time role.

Qualifications

• Strong software engineering fundamentals.
• Experience building non-trivial systems in Python (data pipelines, test/eval infrastructure, sandboxes, or backend services).

Responsibilities

• Turning a capability gap into thousands of verifiable tasks for the agent to root-cause.
• Building environments that resemble production with real dependencies and realistic apps.
• Designing graders for open-ended work that distinguish good solutions without unfairly penalizing valid approaches.
• Building automated checks to catch reward hacking, leaked answers, and broken environments before data reaches training.
• Scaling from thousands to millions of tasks with trusted filters and judges.

Skills

Python

Data pipelines

Eval infra

Backend services

Sandbox environments

Job description

SpaceXAI is hiring a Software Engineer for the RL Data team to shape training data and evaluation for agents. You will build environments that mimic production codebases and design graders to evaluate open-ended work, turning messy problems into scalable, verifiable data pipelines.

You’ll work on failing-proof data generation through automated checks and robust data production systems, with emphasis on reliability and reproducibility in a remote, full-time role.