Software Engineer, RL Data

What this role involves

Anthropic seeks a senior software engineer to build data collection pipelines, human feedback tooling, and execution environments for reinforcement learning data used to train Claude. The role involves end-to-end ownership of infrastructure, QA frameworks, and collaboration with research teams. Required experience includes strong engineering skills and a track record of owning major projects in fast-paced environments.

Skills this posting asks for

• python
• typescript
• docker
• kubernetes
• cloud infrastructure
• reinforcement learning
• data pipelines
• quality assurance
• human feedback
• sandboxing
• evals
• graders
• data engineering
• api integration
• cli
• mcp servers
• user experience
• internal platforms
• security
• compliance

Requirements

• Level: senior

From the employer’s posting

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, en…