Software Engineer, RL Data at Anthropic

Hybrid - San Francisco, CA; New York City, NY

Apply
More jobs at Anthropic

This senior, foundational role on Anthropic's RL Data team involves building systems that produce high‑quality reinforcement learning data for Claude, including data collection pipelines, human feedback tooling, execution environments, and quality assurance. You will own significant parts of the stack end‑to‑end, design architecture, develop pipelines, improve QA frameworks, build interfaces for human data collection, harden execution environments, and collaborate with domain experts and partners.

Salary

R$ 320,000 - 485,000

Requirements

Skills

  • Track record of owning major projects end-to-end in fast‑paced, ambiguous environments
  • Trusted to run key projects; lead and inspire others, plan workstreams, collaborate cross‑functionally, and eliminate blockers
  • Strong software engineering skills in at least one modern programming language (Python, TypeScript) and ability to pick up new tools quickly
  • Familiarity with Docker, Kubernetes, and common cloud infrastructure
  • Effective use of AI tools in day‑to‑day work
  • Care about the societal impacts of your work
  • Experience with reinforcement learning on LLMs, particularly on the data side (creating evals, environments, rewards, graders, or training data)
  • Experience helping organizations use AI more effectively, including integrating with third‑party tools via APIs, CLIs, and MCP servers
  • Strong data engineering skills: pipelines handling large volumes reliably, LLM‑powered enrichment steps, focus on improving data quality
  • Experience shipping user‑facing products or internal platforms people love, interviewing users, hunting down friction, measurably improving experience
  • Basic familiarity with AI safety or security research

Responsibilities

  • Own significant parts of our stack end‑to‑end, from technical architecture through operational work that makes it succeed
  • 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 the teams and domain experts who use our systems day‑to‑day, and work with operations, security, and compliance partners to roll our systems out to new users and vendors

Technologies

PythonTypeScriptDockerKubernetesCloud infrastructureAI toolsReinforcement learningLLMsData collection pipelinesQA frameworksExecution environments

Share job

See if your resume is ready for this job

See how our AI can optimize your resume and improve your chances for this role.