Staff+ Software Engineer, ML Sampling Path
Anthropic · San Francisco, CA
About this role
**About Anthropic** Anthropic’s mission is to create reliable, interpretable, and steerable AI systems—safe and beneficial for users and society. **About the role** The Safeguards ML Sampling Path team builds and operates the production services that power Claude’s safety systems. These services sit on the token generation path across every platform Claude runs on—so every millisecond of added latency matters. You’ll help keep p99 latency flat as traffic grows, build for robustness when dependencies time out or partially fail, and ship changes safely to a system that cannot go down. **What you’ll do** - Design, build, and operate backend systems that process every token on the generation path for Claude requests, including the streaming contract with the API and inference engines. - Own latency and reliability end to end: define and maintain SLOs and error budgets for added latency, time-to-first-token, and availability; lead incident response and postmortem follow-through. - Ship changes to the hot path rapidly but safely (canaried/gradual rollouts, error budget and latency gating, fast rollbacks) and drive per-token performance—chasing tail latency and keeping cost flat as traffic, models, and checks per request grow. - Set technical direction for the sampling path: lead design reviews, make latency/reliability/cost trade-off calls with inference and research teams, mentor engineers, and raise the operational bar across the Safeguards organization. **You may be a good fit if you** - Have designed, built, and operated high-QPS systems at global scale with production accountability (incident response, outages, and postmortem-driven remediation). - Have a strong foundation in distributed systems (replication, consistency tradeoffs, failure modes, and SLO management under load). - Design for graceful degradation (plan for slow dependencies, dropped streams, or partially rolled-out deploys; ensure predictable degradation instead of failure). - Have shipped broad/all-encompassing changes to mission-critical systems (e.g., database migrations, interface changes, rewrites). **Strong candidates may also have** - 8+ years of industry software engineering experience. - Familiarity with LLM inference systems and transformer-based models (not required, but a plus). **Compensation** Annual salary range: **$320,000–$485,000 USD**. **Logistics** - **Minimum education:** Bachelor’s degree or equivalent combination of education, training, and/or experience - **Required field of study:** Relevant to the role (via coursework, training, or professional experience) - **Minimum years of experience:** Correlates with internal job level requirements - **Location-based hybrid policy:** Expected to be in one of the offices at least **25%** of the time (some roles may require more) - **Visa sponsorship:** Yes—Anthropic makes reasonable efforts to sponsor visas, with support from an immigration lawyer **Safety note** Anthropic recruiters only contact candidates from **@anthropic.com** email addresses (and may use vetted recruiting agencies). Legitimate recruiters will never ask for money/fees/banking information before your first day. **How we’re different** Anthropic values high-impact, collaborative research and communication, working as a cohesive team on a few large-scale efforts. **Come work with us** Public benefit corporation headquartered in San Francisco, offering competitive compensation and benefits, optional equity donation matching, generous
Listing freshness
CronJobs last confirmed this listing 21h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.