Software Engineer, RL Data

About the role

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 s role is foundational and hands‑on, shaping our technical direction and what we build first. You will own significant parts of our stack end‑to‑end, from technical architecture to the operational work that makes it succeed.

• Own significant parts of the stack end‑to‑end, from technical architecture through operational work.
• Build data collection pipelines, read the transcripts they produce, and iterate on prompts, evals, and graders until the output is good.
• Develop and improve QA frameworks to catch reward hacking and ensure environment quality.
• Build interfaces that make collecting human data fast and painless for the people providing it.
• Harden execution environments—sandboxing, snapshotting, tool coverage—so tasks hold up at training scale.
• Embed with teams and domain experts who use our systems day‑to‑day: design pipelines and evals with them, support them directly, and ship required improvements.
• Work with operations, security, and compliance partners to roll our systems out to new users, and manage technical relationships with external data vendors.

• Strong software engineering skills and proficiency in at least one modern programming language (Python or Type Script preferred).
• Experience designing, building, and running backend systems or infrastructure.
• Effective use of AI tools in your own day‑to‑day work.
• Willingness to own problems end‑to‑end, including non‑engineering parts.
• Proactive, open communication and the ability to run a workstream and escape early when something is off.
• Comfort iterating quickly in ambiguous, fast‑changing situations.
• Care about the societal impacts of your work.

• Experience building LLM‑powered systems: prompt pipelines, evals, or products with models in the loop.
• Experience with reinforcement learning on LLMs: creating environments, rewards, graders, or training data.
• Forward‑deployed engineering experience, owner of outcomes rather than just code.
• Experience shipping user‑facing products or internal platforms that users love.
• Experience building data pipelines or integrations that move, transform, and index data from many sources.
• Experience building connectors or integrations with third‑party tools and APIs (e.g., MCP servers).
• Experience with containers, Kubernetes, or simulation infrastructure.
• Experience handling sensitive data or working under tight security controls.
• Experience working with external data vendors.

• Implement QA checks that a model has learned to game and make them robust under heavy optimization pressure.
• Create a review flow that lets a busy expert check an RL task in under five minutes.
• Reduce the time from a rough task idea to a QA‑passed RL task from days to hours.
• Ship fixes that help teams using our platform achieve the greatest impact.
• Harden a sandboxed environment so tasks behave correctly across millions of rollouts.
• Onboard a new data vendor and resolve early friction points.

Annual Salary: $320,000 — $485,000 USD. (This range reflects the role’s on‑target earnings.)

Minimum education:

Bachelor’s degree or equivalent. Minimum years of experience: aligns with internal job level requirements. Location‑based hybrid policy: staff must be in an office at least 25% of the time. Visa sponsorship is available and Anthropic cooperates with immigration lawyers to obtain visas when an offer is made.

Anthropic invites applicants who identify as belonging to underrepresented groups to apply and emphasizes the importance of diverse perspectives in building safe and beneficial AI systems. We encourage anyone who believes they can contribute to submit an application.