Software Engineer (RL Data)

Join Anthropic's RL Data team as a Software Engineer, where you'll build systems that produce high-quality reinforcement learning data for Claude. This foundational role involves hands-on work in pipeline and infrastructure engineering, prompt tuning, and user support. You'll own significant parts of our stack end-to-end, develop QA frameworks, build interfaces for human data collection, and harden execution environments. You'll also collaborate with teams and domain experts, manage technical relationships with external data vendors, and contribute to AI safety research and beneficial deployments of AI.

• Conception, development, and improvement of data collection pipelines and quality assurance frameworks.
• Collaboration with research teams to design and implement reinforcement learning tasks, ensuring high-quality output.
• Management of technical relationships with external data vendors and coordination with operations, security, and compliance partners.
• Effective use of AI tools in your own day-to-day work
• Comfort iterating quickly in ambiguous, fast-changing situations
• Strong software engineering skills and proficiency in at least one modern programming language — we mostly use Python and TypeScript, and care more that you pick new tools up quickly than that you know our exact stack
• Care about the societal impacts of your work
• Experience designing, building, and running backend systems or infrastructure
• Proactive, open communication: you can be trusted to run a workstream, and to escalate early when something's off
• Willingness to own problems end-to-end, including the parts that aren't engineering
• 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
• Time as a forward deployed engineer, founder, or early startup engineer — roles where you owned the outcome, not just the code
• Experience shipping user-facing products, or internal platforms people love: interviewing users, hunting down friction, measurably improving the experience
• 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, such as 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
• Basic familiarity with AI safety or security research
• Bachelor’s degree or an equivalent combination of education, training, and/or experience
• We encourage you to apply even if you do not believe you meet every single qualification