Research Engineer / Research Scientist, RL Frontiers

<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 is how Claude learns to reason, write code, and act autonomously over long horizons. The RL Scaling team works on how RL scales: what happens to throughput, stability, and learning efficiency as models get larger, episodes get longer, and compute grows by orders of magnitude, and what has to change in our algorithms and systems to keep getting returns from that scale.</p> <p>This role sits squarely across research and engineering. You'll develop next-generation architectures and RL algorithms, take them from a small-scale result to a frontier-scale run, and understand every place they behave differently along the way. You'll build the systems that set how fast the team can iterate: how many experiments, at what scale, and how quickly we can trust the results. And you'll work on Anthropic's largest and fastest RL runs, where the gap between a good idea and a working one is often a problem no one has solved yet.</p> <h2>Key responsibilities</h2> <ul> <li>Study how RL training and sampling scale with model size, context length, and compute, and find the algorithmic and systems changes that keep scaling efficient</li> <li>Develop next-generation model architectures and RL algorithms, and make them run efficiently at frontier scale</li> <li>Take promising small-scale results to frontier-scale runs, and diagnose why they behave differently when they get there, whether the cause is numerical, algorithmic, or systemic</li> <li>Build the experimental infrastructure that sets research velocity: fast, reproducible comparisons of architecture and algorithm variants at meaningful scale</li> <li>Own end-to-end performance of our largest RL runs, from research code down to the hardware</li> <li>Build performance and cost models for proposed architecture and algorithm changes, and use them to decide which ideas get scaled</li> <li>Investigate training dynamics at scale, including instabilities, divergence, and throughput regressions, and trace them to root cause</li> </ul> <h2>Minimum qualifications</h2> <ul> <li>Deep familiarity with modern transformer language models, including their architecture, training dynamics, and the behavior of large-scale optimization</li> <li>Hands-on experience training large models in a distributed setting, including the tradeoffs between