Senior Backend Engineer, ML Sampling Path - Low Latency

Fdetimes; San Francisco (CA); On-site; USD 320,000 - 485,000; Full time

Benefits offered by this job

Equity donation matching

Generous vacation

Parental leave

Flexible hours

Office in SF

Job summary

Anthropic in San Francisco seeks an experienced Safeguards ML Sampling Path engineer to design, build, and operate backend services powering Claude's safety systems. You will own latency, reliability, and costs, driving guardrails and scalable performance in production.

Lead design reviews with inference and research teams, mentor engineers, and ship changes safely with canaries and gradual rollouts as traffic grows.

Qualifications

• 8+ years of industry software engineering experience.
• Familiarity with LLM inference systems and transformer-based models is a plus.
• Experience designing for latency, reliability, and cost trade-offs in production systems.

Responsibilities

• Design, build, and operate backend systems processing token generation paths for Claude requests.
• Own latency and reliability: define SLOs and budgets; lead incident response and postmortems.
• Ship changes with canary releases, gating, and fast rollbacks; optimize per-token performance.
• Set technical direction for the sampling path; lead design reviews and mentor engineers.

Skills

High QPS systems

Distributed systems

SLO management

Incident response

Canary deployments

Postmortems

Education

Bachelor's degree

Job description

Anthropic in San Francisco seeks an experienced Safeguards ML Sampling Path engineer to design, build, and operate backend services powering Claude's safety systems. You will own latency, reliability, and costs, driving guardrails and scalable performance in production.

Lead design reviews with inference and research teams, mentor engineers, and ship changes safely with canaries and gradual rollouts as traffic grows.