Performance Engineer, Inference Systems

<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><strong>About the Role</strong></h2> <p>Anthropic&39;s inference fleet serves Claude to millions of users across our own products and the world&39;s largest cloud platforms. The stack that makes this possible is deep and tightly coupled: accelerator kernels, model servers, distributed routing, autoscaling, capacity management. Every layer affects the others, often in ways that are hard to see in isolation.</p> <p>The Inference System Dynamics team is responsible for understanding that whole system and holding it to a high bar across four dimensions: <strong>throughput, latency, reliability, and correctness</strong>. We measure how the fleet performs against its theoretical performance frontier, run cross-layer investigations to explain the gaps, and own the correctness checks that make sure Claude&39;s outputs are right, not just fast, across hardware platforms and serving configurations. We don&39;t own the individual components. We instrument and model them, find the highest-leverage opportunities across them, and partner with the owning teams to land the wins.</p> <p>You&39;ll work across all four areas. One week that might mean tracing a tail-latency regression from request timing down through routing and batching into a kernel overhead; the next it might mean tightening a correctness eval so it catches an output regression introduced by a quantization change. We&39;re looking for performance engineers who treat correctness as part of