Staff Software Engineer, AI Safety & Abuse Detection

Anthropic; San Francisco (CA); Hybride; USD 320 000 - 485 000; Plein temps

Avantages offerts par ce poste

Competitive compensation and benefits

Equity donation matching (optional)

Generous vacation and parental leave

Flexible working hours

Office in San Francisco

Résumé du poste

Anthropic, a San Francisco–based AI safety company, seeks software engineers for the Safeguards team to build safety and oversight mechanisms for our AI systems. You will work to monitor models, prevent misuse, and enforce our terms of service while improving user well-being.

Responsibilities include developing monitoring systems, building abuse detection, surfacing patterns to researchers, and creating robust defenses for real-time safety improvements at scale.

Qualifications

• Bachelor’s degree in Computer Science, Software Engineering or comparable experience
• Proficiency in Python and TypeScript
• Ability to work across the stack
• Strong communication skills to explain technical concepts to non-technical stakeholders

Responsabilités

• Develop monitoring systems to detect unwanted model behaviors and surface results to analysts
• Build abuse detection mechanisms and infrastructure
• Surface abuse patterns to research teams to harden models
• Build multi-layered defenses for real-time safety improvements at scale

Connaissances

Python

TypeScript

Cross-stack

Communication

Formation

Bachelor’s in CS/Software Eng

Description du poste

Anthropic, a San Francisco–based AI safety company, seeks software engineers for the Safeguards team to build safety and oversight mechanisms for our AI systems. You will work to monitor models, prevent misuse, and enforce our terms of service while improving user well-being.

Responsibilities include developing monitoring systems, building abuse detection, surfacing patterns to researchers, and creating robust defenses for real-time safety improvements at scale.