Staff Software Engineer (Safeguards Infrastructure)

Join Anthropic, a leading AI safety and research company, as a Staff Software Engineer on the Safeguards team. In this role, you will build foundational systems for safety, oversight, and intervention mechanisms of AI systems. You will focus on monitoring models, preventing misuse, and ensuring user well-being. Your technical skills will uphold principles of safety, transparency, and oversight. You will develop systems for data storage and management, metric and evaluation systems, and tooling for human and agentic review. Additionally, you will ensure the day-to-day running of Safeguards systems and build robust multi-layered defenses for real-time improvement of safety mechanisms.

• Contribuer à la construction des systèmes fondamentaux pour la sécurité, la surveillance et les mécanismes d'intervention de nos systèmes d'IA.
• Développer les systèmes fondamentaux qui alimentent les garanties, y compris l'infrastructure pour le stockage et la gestion des données, les systèmes de métriques et d'évaluation.
• Assurer le bon fonctionnement des systèmes de garanties au quotidien et maintenir un niveau opérationnel élevé qui sert à la fois la sécurité et les clients.
• 7+ years of experience in a software engineering position
• Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience
• Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience
• We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed
• Strong communication skills and ability to explain complex technical concepts to non-technical stakeholders
• Ability to work across the stack
• Bachelor’s degree in Computer Science, Software Engineering or comparable experience
• Proficiency in Python
• Have experience building trust and safety, anti-spam, fraud or abuse detection and mitigation mechanisms and interventions for AI/ML systems
• Have worked closely with operational teams to build custom internal tooling
• Have experience building metrics and measurement systems or data and privacy management systems
• Be proficient in TypeScript or Rust
• Have experience with Claude Code or similar agentic coding tools