Software Engineer, RL Data

Overview

Senior Software Engineer (RL Data) on a new team building foundational systems for generating high-quality reinforcement learning data for Claude.

What you'll do

• Make architecture decisions that shape early team work.
• Own significant parts of the stack end-to-end, from architecture to operations.
• Build data collection pipelines and iterate on prompts, evals, and graders.
• Develop QA frameworks to catch reward hacking and ensure environment quality.
• Build interfaces for fast, low-friction collection of human feedback data.
• Harden execution environments for training-scale reliability.
• Coordinate with operations, security, and compliance partners to roll out systems to users and vendors.

What you'll need

• Experience owning major projects end-to-end in fast-paced, ambiguous environments.
• Ability to lead and inspire others, plan workstreams, and manage cross-functional collaboration.
• Strong software engineering skills in at least one modern programming language (primarily Python and TypeScript).
• Plus: familiarity with Docker, Kubernetes, and common cloud infrastructure.
• Effective use of AI tools in daily work.
• Basic familiarity with AI safety or security research (preferred).

Details

• Annual compensation range: $320,000–$485,000 USD.
• Location-based hybrid policy: expected in an office at least 25% of the time.
• Visa sponsorship is available for some roles/candidates.