Software Engineer, RL Data

About Anthropic

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems.

We want AI to be safe and beneficial for our users and for society as a whole.

Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

About the role

This is a senior, foundational role on a new team: you'll make architecture decisions the rest of the team builds on, and help shape what we build first.

The work is hands‑on and varied.

Some weeks you'll be deep in pipeline or infrastructure engineering; others you'll be tuning prompts until the output is good, or sitting with a research team that depends on your systems and shipping the fixes they need.

We’re looking for experienced engineers who own outcomes end‑to‑end — down to reading transcripts, supporting users, and wrangling vendors.

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.

Our goal is to make Claude great at real work — especially the work that matters most, like AI safety research and beneficial deployments of AI. (To be upfront: this is dual‑use work — it advances general capabilities too.)

Key responsibilities

• Own significant parts of our stack end‑to‑end, from technical architecture through the unglamorous 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.
• Minimum qualifications
• A track record of owning major projects end‑to‑end in fast‑paced, ambiguous environments — for example as a founder or CTO, forward deployed engineer, tech lead, founding engineer at a startup, or creator of a substantial open‑source project.
• Trusted to run key projects: you lead and inspire others, plan workstreams effectively, collaborate with cross‑functional stakeholders, and proactively eliminate or eliminate blockers.
• Strong software engineering skills in at least one modern programming language — we mostly use Python and Type Script, but care more that you pick new tools up quickly than that you know our exact stack.

Familiarity with Docker, Kubernetes, and common cloud infrastructure is a plus.

• Effective use of AI tools in your own day‑to‑day work.
• Care about the societal impacts of your work.
• Preferred qualifications
• 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 that handle large volumes reliably in production, LLM‑powered enrichment steps, and a focus on improving data quality.
• Experience shipping user‑facing products or internal platforms people love: interviewing users, hunting down friction, measurably improving the experience.
• Basic familiarity with AI safety or security research.
• Representative projects
• Take a data collection pipeline from research prototype to a production service that serves many research teams — collection, human validation, grading, and everything in between.
• Own the program of developing sandboxed execution environments realistic enough for long‑horizon, high‑tool‑use agentic tasks — and harden them so they behave correctly across millions of rollouts in a frontier training run.
• Bring a new data source online — from first conversation with a partner organization to data flowing into production training runs — coordinating with product, security, privacy, legal, and infrastructure teams along the way.
• Own the QA layer that decides which tasks make it into Claude’s training: automated checks and expert review flows (a busy domain expert should be able to validate a task in under five minutes) that hold up when a frontier model learns to game them.
• Cut the time from “rough task idea” to “task in a production training run” from days to hours.

You’d own the direction: figure out where the bottlenecks actually are, then automate, redesign, or delete the steps in the way.

The annual compensation range for this role is listed below.

Logistics

Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience.

Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience.

Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position.

Location‑based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.

Visa sponsorship: We do sponsor visas!

However, we aren’t able to successfully sponsor visas for every role and every candidate.

But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

#J-18808-Ljbffr