Backend Engineer, Safe AI Sampling Path

Anthropic Limited; San Francisco (CA); Hybrid; USD 320,000 - 485,000; Full time

Benefits offered by this job

Competitive compensation

Equity donation matching

Vacation and parental leave

Flexible working hours

Office space

Job summary

Anthropic Limited is seeking a senior engineer for the Safeguards ML Sampling Path that powers Claude safety systems. You will design, build, and operate backend systems processing token generation, ensuring low latency and high reliability across platforms.

You will own latency budgets, lead incident response, and drive safe, scalable deployments with canaries and gradual rollouts, while guiding architecture with researchers and engineers.

Qualifications

• Designed, built, and operated high-QPS systems in production.
• Strong foundation in distributed systems and SLO management under load.
• Experience designing for graceful degradation and safe rollouts.
• Proven ability to ship changes to mission-critical systems.

Responsibilities

• Design, build, and operate backend systems that process token generation for Claude requests.
• Own latency and reliability end-to-end; define and maintain SLOs and error budgets.
• Ship changes to the hot path with canary rollouts, gating, and safe rollbacks.
• Set technical direction for the sampling path; mentor engineers and raise the operational bar.

Skills

High QPS systems

Distributed systems

Incident response

SLO management

Education

Bachelor's degree

Job description

Anthropic Limited is seeking a senior engineer for the Safeguards ML Sampling Path that powers Claude safety systems. You will design, build, and operate backend systems processing token generation, ensuring low latency and high reliability across platforms.

You will own latency budgets, lead incident response, and drive safe, scalable deployments with canaries and gradual rollouts, while guiding architecture with researchers and engineers.