Software Engineer, RL Data

Anthropic's RL Data team builds the systems that produce high-quality reinforcement learning data for Claude: data collection pipelines, human feedback tooling, the execution environments RL tasks run in, and the quality assurance that keeps training data trustworthy at scale. This is a senior, foundational role on a new team, involving architecture decisions and hands-on, varied work — from pipeline and infrastructure engineering to tuning prompts and supporting research teams.

• Own significant parts of the 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 that make collecting human data fast and painless.
• Harden execution environments — sandboxing, snapshotting, tool coverage — so tasks hold up at training scale.
• Embed with teams and domain experts, working with operations, security, and compliance partners.

Minimum: a track record of owning major projects end-to-end in fast-paced, ambiguous environments; strong software engineering skills in at least one modern language (mostly Python and TypeScript); familiarity with Docker, Kubernetes, and common cloud infrastructure is a plus; effective use of AI tools; care about societal impacts. Preferred: experience with reinforcement learning on LLMs, particularly on the data side; experience helping organizations use AI effectively, including integrating with third-party tools via APIs, CLIs, and MCP servers; strong data engineering skills; experience shipping user-facing products or internal platforms; basic familiarity with AI safety or security research.

Annual salary: $320,000—$485,000 USD.

Minimum education: Bachelor's degree or equivalent combination of education, training, and/or experience. Location-based hybrid policy: all staff expected in one of our offices at least 25% of the time. Visa sponsorship is offered.