Performance Engineer, Inference Systems San Francisco, CA | New York City, NY | Seattle, WA

Anthropic; San Francisco (CA); On-site; USD 350,000 - 850,000; Full time

Benefits offered by this job

Visa sponsorship

Flexible hybrid work policy

Job summary

Anthropic is looking for a Performance Engineer to work on its Inference System Dynamics team. You will focus on optimizing throughput, latency, and correctness across systems serving millions of users. You will also improve the evaluation pipeline for model outputs and build observability tools for performance metrics.

The ideal candidate has hands-on experience in performance engineering, strong data analysis skills, and proficiency in Python. This role offers a hybrid work environment and is integral to maintaining the high standards of AI systems.

Qualifications

• 1+ years of hands-on performance engineering experience in complex production systems.
• Ability to read and contribute to large production Python codebases.
• Solid experience with data analysis tools like SQL or pandas.

Responsibilities

• Run performance investigations across throughput, latency, and reliability.
• Improve correctness evaluation pipeline for model output quality.
• Build observability and dashboards for performance metrics.

Skills

Performance engineering experience

Proficiency in Python

Data analysis skills

Communication of quantitative results

Interest in correctness

Education

Bachelor’s degree or equivalent

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 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

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 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

Preferred Qualifications

• Experience with ML systems, especially training or inference infrastructure or general LLM serving stacks. Direct large-scale inference experience is a strong 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

Representative Projects

• Trace a 350ms latency gap on a new accelerator platform from end-to-end request timing down to a server scheduling overhead, quantify the win, and land the fix directly or with the owning team
• Redesign the correctness eval gate: determine which signals reliably catch real model-output regressions versus noise, and make it the trusted release criterion across hardware backends
• Build a FLOPs funnel that breaks down where compute actually goes across the fleet, exposing the gap between achieved throughput and kernel rooflines
• Root-cause a numerical divergence between two hardware platforms to a specific kernel change, and define the acceptance threshold going forward
• Model the latency–cost impact of changing batch-sizing and utilization targets, and turn the result into the signal the autoscaler uses in production

Deadline to apply: None. Applications will be reviewed on a rolling basis.

The annual compensation range for this role is listed below.

$350,000 - $850,000 USD

Logistics

Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience

Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience

Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position

Location-based hybrid policy: 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.

Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

We encourage you to apply even if you do not believe you meet every single qualification.

As set forth in Anthropic’s Equal Employment Opportunity policy, we do not discriminate on the basis of any protected group status under any applicable law.