Software Engineer, RL Data

Build systems for high-quality reinforcement learning data for Claude.

• •Anthropic's mission is to create reliable, interpretable, and steerable AI systems.
• •This senior, foundational role on a new team involves making architecture decisions and shaping the team's initial focus.
• •The work is hands-on and varied, ranging from pipeline and infrastructure engineering to prompt tuning and supporting research teams.
• •Key Responsibilities Own significant parts of our stack end-to-end, from technical architecture through operational work.
• •Build data collection pipelines, iterate on prompts, evals, and graders.
• •Develop and improve QA frameworks to catch reward hacking and ensure environment quality.
• •Build interfaces for fast and painless human data collection.
• •Harden execution environments for training scale.
• •Requirements Track record of owning major projects end-to-end in fast-paced, ambiguous environments.
• •Trusted to run key projects, leading and inspiring others, planning workstreams, and collaborating with stakeholders.