Software Engineer, RL Data

Anthropics 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.

This is a senior foundational role on a new team: youll 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 youll be deep in pipeline or infrastructure engineering; others youll 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. Were looking for experienced engineers who own outcomes end-to-end down to reading transcripts supporting users and wrangling vendors.

Anthropics 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.)

• 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.

• 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 escalate blockers.
• Strong software engineering skills in at least one modern programming language we mostly use Python and TypeScript 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.

• 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.

• 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 Claudes 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. Youd own the direction: figure out where the bottlenecks actually are then automate redesign or delete the steps in the way.

Minimum education: Bachelors 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 arent 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.

We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy so we urge you not to exclude yourself prematurely and to submit an application if youre interested in this work. We think AI systems like the ones were building have enormous social and ethical implications. We think this makes representation even more important and we strive to include a range of diverse perspectives on our team.

Your safety matters to us. To protect yourself from potential scams remember that Anthropic recruiters only contact you some cases we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money fees or banking information before your first day. If youre ever unsure about a communication dont click any linksvisit for confirmed position openings.

We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact advancing our long-term goals of steerable trustworthy AI rather than work on smaller and more specific puzzles. We view AI research as an empirical science which has as much in common with physics and biology as with traditional efforts in computer science. Were an extremely collaborative group and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such we greatly value communication skills.

The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic including: GPT-3 Circuit-Based Interpretability Multimodal Neurons Scaling Laws AI & Compute Concrete Problems in AI Safety and Learning from Human Preferences.

Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits optional equity donation matching generous vacation and parental leave flexible working hours and a lovely office space in which to collaborate with colleagues. Guidance on Candidates AI Usage:Learn aboutour policy for using AI in our application process.