Anthropic
AI
PerformanceEngineer,InferenceSystems
Neural analysis suggests this role is
optimal for Mid+ candidates.
“Performance Engineer, Inference Systems at Anthropic. Skills: Performance engineering, Inference systems, Correctness evaluation, Data analysis, Python. Run cross-layer performance investigations across throughput, latency, and reliability. Size the gap between actual fleet performance and theoretical rooflines”
What You'll Achieve.
Hold the inference fleet to a high bar across four dimensions: throughput, latency, reliability, and correctness; Measure how the fleet performs against its theoretical performance frontier; Run cross-layer investigations to explain performance gaps; Own the correctness checks that make sure Claude's outputs are right, not just fast, across hardware platforms and serving configurations; Land the highest-impact optimizations your analysis surfaces
Industry & Context.
Root-cause investigation; Cross-layer performance investigations; Sizing the gap between actual fleet performance and theoretical rooflines; Identifying root causes; Quantifying the value of closing gaps; Reasoning about performance concepts
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.
What They're Looking For.
Must Have
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
Nice to Have
Experience with ML systems, especially training or inference infrastructure or general LLM serving stacks., Direct large-scale inference experience is a plus, Familiarity with GPU/TPU/accelerator performance concepts (memory bandwidth, kernel overheads, quantization, collective communication)., Reasoning about these matters more than having written kernels yourself, 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, Comfortable having impact through influence and evidence rather than direct ownership
What You'll Do.
Run cross-layer performance investigations across throughput
Size the gap between actual fleet performance and theoretical rooflines
Identify root causes of performance gaps
Quantify the value of closing performance gaps
Own and improve the correctness evaluation pipeline that validates model output quality across hardware platforms
and serving configurations
Lead investigation when correctness evaluation pipeline catches a regression
and modeling tools that make throughput
and their interactions legible across the stack
and capacity teams to prioritize and land the highest-impact optimizations
Stack-rank a large surface area of opportunities by impact and effort
How You'll Work.
Team & Collaboration
Partner with kernel, serving, routing, autoscaling, and capacity teams to prioritize and land the highest-impact optimizations your analysis surfaces; Communicate quantitative results clearly in writing to influence priorities on teams you don't manage; Collaborative group; Host frequent research discussions
Communication Scope
Communicate quantitative results clearly in writing; Communication skills
Process & Methodology
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
Full Job Description
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. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. 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 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. The Inference System Dynamics team is responsible for understanding that 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. We don'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. You'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're looking for performance engineers who treat correctness as part of performance. Key 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 i
Applying for this Performance Engineer, Inference Systems role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
How to Apply on Greenhouse
- Create a Greenhouse profile before applying — it saves time across multiple applications.
- Upload your resume as a PDF; the parser handles it better than Word.
- Answer all knockout questions carefully — wrong answers auto-reject before a human sees you.
- Enable email notifications to track application status in real time.
ANONYMOUS · UNFILTERED
What do employees actually say about Anthropic?
Real rants from real employees. Read before you apply.