Performance Engineer, Inference Systems

Anthropic
San Francisco, California, United States
Full Time
Hybrid
Senior
USD 350,000 – 850,000
Bachelor Degree
Engineering Information Technology Telecommunications

Posted 2 months ago

Apply to this job and hundreds more automatically

Get Started
Excellent 4.7

Job summary

The role involves performance engineering for inference systems, focusing on optimizing throughput, latency, reliability, and correctness across hardware platforms within Anthropic's AI inference fleet. Key responsibilities include cross-layer performance investigations, improving correctness evaluation pipelines, building observability tools, and partnering with various teams to optimize system performance.

Responsibilities

Conduct cross-layer performance investigations to optimize throughput, latency, and reliability of inference systems. Develop observability tools and correctness evaluation pipelines to validate model output quality across hardware platforms.

Qualifications

data analysis latency optimization pandas performance engineering profiling Python roofline analysis root-cause investigation SQL throughput optimization

Requires hands-on experience in performance engineering, proficiency in Python, and strong data analysis skills. A background in ML infrastructure, accelerator performance, and reliability engineering for high-throughput services is highly preferred.

English

Benefits

  • Competitive Compensation
  • Optional Equity Donation Matching
  • Generous Vacation
  • Parental Leave
  • Flexible Working Hours
  • Office Space

Company

Anthropic

Anthropic

linkedin
Research Services
Location
San Francisco, California, United States

Apply to this job and hundreds more automatically

Get Started
Excellent 4.7
Pete DeQuarto avatar
Pete DeQuarto

AIApply is a total game-changer. Thanks to Auto-Apply, I have been applying to jobs I would never even have come across otherwise!

Akarshak Tanwar avatar
Akarshak Tanwar

In one week I applied to over 150 jobs and locked in 2 confirmed interviews, with a support team that was quick to respond. The auto-apply feature is fascinating and a real pleasure to use!

JC
Julian Carlin

It really worked. In under 48 hours it had applied to 100 jobs on my behalf without any time or effort from me. I am looking forward to seeing how it keeps improving.