Anthropic’s inference fleet serves Claude to millions of users across its own products and the world's largest cloud platforms. The Inference System Dynamics team is responsible for understanding the entire system and holding it to a high bar across throughput, latency, reliability, and correctness. The role involves cross‑layer performance investigations, improving correctness evaluation pipelines, building observability and modeling tools, partnering with various system teams, and prioritizing high‑impact optimizations.
Performance Engineer, Inference Systems at Anthropic
Hybrid - San Francisco, CA; New York City, NY; Seattle, WA
More jobs at AnthropicSalary
USD 350,000 - 850,000
Requirements
Skills
- 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 you didn’t write
- Solid data analysis skills (e.g. SQL, pandas, or similar) sufficient to turn raw telemetry into clear findings
- Ability to communicate quantitative results clearly in writing to influence priorities on teams you don't manage
- Genuine interest in correctness as an engineering discipline: numerics, evaluation design, regression detection
Responsibilities
- Run cross‑layer performance investigations across throughput, latency, and reliability, sizing the gap between actual fleet performance and theoretical rooflines, identifying root causes, and quantifying the value of closing them
- Own and improve the correctness evaluation pipeline that validates model output quality across hardware platforms, numerics, and serving configurations, and lead the investigation when it catches a regression
- Build the observability, dashboards, and modeling tools that make throughput, latency, cost, reliability, correctness, and their interactions legible across the stack
- Partner with kernel, serving, routing, autoscaling, and capacity teams to prioritize and land the highest‑impact optimizations your analysis surfaces
- Ruthlessly stack‑rank a large surface area of opportunities by impact and effort, and say no to the ones that don't make the cut
Technologies
PythonSQLpandasGPUTPUaccelerator performance conceptsautoscalingload balancingrequest routingtail latencymodel evaluationnumerical regression detectionobservabilitytelemetry for distributed systems
See if your resume is ready for this job
See how our AI can optimize your resume and improve your chances for this role.