The Safeguards ML Infra team at Anthropic builds and operates the production infrastructure that powers Claude’s safety systems. This role focuses on designing, building, and maintaining scalable backend services, observability, SLOs, and incident response across multiple deployment platforms, ensuring reliable safety mechanisms for all Claude requests.
Staff+ Software Engineer, Safeguards ML Infrastructure na Anthropic
Híbrido - San Francisco, CA, United States
Ver mais vagas na AnthropicSalary
USD 320,000 - 485,000
Requirements
Skills
- Proficiency in Python
- Experience with Rust (plus)
- Designed, built, and operated high QPS systems at global scale
- Strong foundation in distributed systems (replication, consistency tradeoffs, failure modes, and SLO management under load)
- Meaningful on-call experience for production systems, including incident response and postmortem-driven improvements
- Desire to close operational gaps and build automation
- Hands‑on experience deploying and operating on cloud platforms (AWS, GCP) at scale
- Approach infrastructure as a platform for other engineers
- 8+ years of industry software engineering experience
- Experience building deployment and rollout systems with canary analysis, automated validation, or progressive rollout controls
- History of reducing operational toil through automation, including transitioning teams from manual deployment processes to self‑serve pipelines
- Familiarity with LLM inference systems and operational characteristics of transformer‑based models
- Bachelor’s degree or an equivalent combination of education, training, and/or experience
- Field of study relevant to the role
Responsibilities
- Design, build, and deploy backend services that are critical safety pieces on the token sampling and generation path
- Own and operate the production serving infrastructure for those services across multiple deployment platforms (1P, AWS Bedrock, GCP Vertex)
- Define and maintain SLOs, build observability and alerting systems, and lead incident response for infrastructure on the critical path of every Claude request
- Participate in on‑call and operational‑duty rotations covering service incidents, model provisioning, and time‑sensitive research and safety launches
- Reduce on‑call and on‑duty toil by building automation, tooling, and self‑serve workflows that minimize manual operations
- Build and maintain a safety registry with full provenance to track what is running in production, on which model, and when and by whom it was deployed
- Implement automated post‑deploy validation to ensure correctness is consistent across platforms
- Work closely with ML researchers to productionize new safety techniques, translating experimental work into reliable, scalable production systems
- Contribute to the long‑term goal of platform‑agnostic deployment tooling that brings 3P platforms to parity with 1P operational maturity
Technologies
PythonRustAWSGCPDistributed systemsObservabilityAlertingAutomationSelf‑serve pipelinesLLM inference systemsTransformer‑based models
Descubra se seu currículo está pronto para esta vaga
Veja como nossa IA pode otimizar seu currículo e aumentar suas chances de conseguir esta posição.