Research Engineer, RL Engineering

<div class="content-intro"><h2><strong>About Anthropic</strong></h2> <p>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.</p></div><h2>About the role</h2> <p>Reinforcement learning (RL) is how Claude learns to reason, write code, and act autonomously over long horizons. This role sits on the team that builds and owns the RL training system: the system that trains our production models and that researchers across Anthropic run their experiments on. The team works closely with research teams across the company on the science and engineering of making RL work at scale.</p> <p>As a Research Engineer on the team, you'll work at the center of RL at Anthropic. You'll have a direct view of how RL training behaves at the frontier because the system you own sits underneath both production and research runs. You will use it with collaborators across research teams to understand what is working, what is fragile, and where the next improvements are.</p> <h2>Key responsibilities</h2> <ul> <li>Build, own, and improve the core RL training system that serves Anthropic's production and research runs</li> <li>Work across the stack (orchestration, environments, training, inference, evaluation) wherever the system needs it</li> <li>Study how RL training behaves at scale and contribute to the research that improves it, in collaboration with teams across Anthropic</li> <li>Implement new training methods as stable, fast, well-tested code</li> <li>Improve the speed and efficiency of RL training and evaluation through profiling, optimization, and benchmarking</li> <li>Make the system easier for researchers to build on, through clean abstractions, clear APIs, and automated testing</li> <li>Debug hard problems across the stack, from a run that has quietly drifted to a distributed systems failure that only shows up at scale</li> <li>Communicate results clearly, in writing and in discussion</li> </ul> <h2>Minimum qualifications</h2> <ul> <li>Proficiency in Python and experience working in, debugging, and improving a large ML codebase</li> <li>Experience with large-scale machine learning training (reinforcement learning, pretraining, or post-training) or the systems that support it</li> <li>Experience with at least one modern ML framework (JAX, PyTorch, or similar)</li> <li>Ability to design controlled experiments and reach conclusions you and others can trust</li> <li>Ability to balance research exploration with engineering implementation</li> <li>Strong written and verbal communication skills</li> <li>Care about the societal impacts of your work and are committed to developing safe and beneficial systems</li> </ul> <h2>Preferred qualifications</h2> <ul> <li>Experience with reinforcement learning for large language models, in research, production, or both</li> <li>Experience studying training at scale: scaling behavior, training dynamics, or method development on large models</li> <li>Experience with large-scale distributed training systems</li> <li>Familiarity with LLM architectures and training methodologies</li> <li>Experience working close to a frontier training run</li> <li>Experience profiling and optimizing the performance of ML workloads</li> <li>Experience with RL environments, evaluations, or sandboxed code execution</li> <li>Experience with Rust or C++</li> <li>Enjoy pair programming (we love to pair!)</li> </ul><div class="content-pay-transparency"><div class="pay-input"><div class="description"><p>The annual compensation range for this role is listed below. </p> <p>For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.</p></div><div class="title">Annual Salary:</div><div class="pay-range"><span>$500,000</span><span class="divider">—</span><span>$850,000 USD</span></div></div></div><div class="content-conclusion"><h2><strong>Logistics</strong></h2> <p><strong>Minimum education: </strong>Bachelor’s degree or an equivalent combination of education, training, and/or experience</p> <p><strong>Required field of study: </strong>A field relevant to the role as demonstrated through coursework, training, or professional experience</p> <p><strong>Minimum years of experience: </strong>Years of experience required will correlate with the internal job level requirements for the position</p> <p><strong>Location-based hybrid policy:</strong> 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.</p> <p><strong data-stringify-type="bold">Visa sponsorship:</strong> 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.</p> <p><strong>We encourage you to apply even if you do not believe you meet every