Performance Engineer, Inference Systems

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. About the Role Anthropic's inference fleet serves Claude to millions of users across our own products and the world's largest cloud platforms. The Inference System Dynamics team is responsible for understanding the whole system and holding it to a high bar across four dimensions: throughput, latency, reliability, and correctness. 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's outputs are right — not just fast — across hardware platforms and serving configurations. Key Responsibilities • Run cross-layer performance investigations across throughput, latency, and reliability; size the gap between actual fleet performance and theoretical rooflines • Own and improve the correctness evaluation pipeline that validates model output quality across hardware platforms, numerics, and serving configurations • Build the observability, dashboards, and modeling tools that make throughput, latency, cost, reliability, and correctness legible across the stack • Partner with kernel, serving, routing, autoscaling, and capacity teams to prioritize and land the highest-impact optimizations • Ruthlessly stack-rank a large surface area of opportunities by impact and effort Representative Projects • Trace a 350ms latency gap on a new accelerator platform from end-to-end request timing down to a server scheduling overhead • Redesign the correctness eval gate to reliably catch real model-output regressions • Build a FLOPs funnel that breaks down where compute actually goes across the fleet • Root-cause a numerical divergence between two hardware platforms to a specific kernel change Compensation: $350,000 – $850,000 USD annually Anthropic offers competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, and flexible working hours. Hybrid policy: staff expected in office at least 25% of the time.

Minimum Qualifications • Hands-on performance engineering experience: profiling, roofline analysis, latency/throughput optimization, and root-cause investigation in complex production systems • Proficiency in Python, with the ability to read, instrument, and contribute to large production codebases • Solid data analysis skills (SQL, pandas, or similar) sufficient to turn raw telemetry into clear findings • Ability to communicate quantitative results clearly in writing to influence priorities • Genuine interest in correctness as an engineering discipline: numerics, evaluation design, regression detection Preferred Qualifications • Experience with ML systems, especially training or inference infrastructure or general LLM serving stacks • Familiarity with GPU/TPU/accelerator performance concepts (memory bandwidth, kernel overheads, quantization, collective communication) • Experience with reliability engineering for high-throughput services: autoscaling, load balancing, request routing, tail latency • Experience with model evaluation or numerical regression-detection pipelines • Experience building observability or telemetry for distributed systems Minimum education: Bachelor's degree or equivalent combination of education, training, and/or experience.