Software Engineer, RL Data
Core
Building systems that produce high-quality reinforcement learning data for Claude, including data collection pipelines, human feedback tooling, execution environments, and quality assurance frameworks.
Role type
Senior IC backend engineer (RL data infrastructure)
Builds
Data collection pipelines, human feedback interfaces, sandboxed execution environments, and QA frameworks for RL training data
Domain
AI safety research / Reinforcement Learning / LLM training infrastructure
Deliverable
production ML models
Required skills
Backend systems design, infrastructure engineering, Python, TypeScript, prompt engineering, evaluation framework design, sandboxing, vendor management
Preferred skills
LLM-powered systems, reinforcement learning on LLMs, containerization, Kubernetes, simulation infrastructure, sensitive data handling, external API integrations
Technologies
Python, TypeScript, Kubernetes, containers
Responsibilities
Design and build data collection pipelines and human feedback interfaces; develop QA frameworks to detect reward hacking; harden execution environments for training scale; embed with domain experts to iterate on system improvements; manage technical relationships with external data vendors
Seniority
Senior, hands-on IC
