Software Engineer, Safeguards
Software Engineer, Safeguards
Anthropic
Anthropic is seeking experienced software engineers to join their Safeguards team, focusing on building safety and oversight mechanisms for AI systems. The role involves developing monitoring systems, abuse detection mechanisms, and collaborating with research teams to enhance model safety. Candidates should have a strong background in software engineering, particularly in integrity and abuse detection, and be proficient in Python and Typescript.
Qualification
- Bachelor’s degree in Computer Science, Software Engineering, or comparable experience.
- 5-10+ years of experience in software engineering, focusing on integrity, spam, fraud, or abuse detection.
- Proficiency in Python and Typescript.
- Ability to work across the stack.
- Strong communication skills to explain technical concepts to non-technical stakeholders.
Responsibility
- Develop monitoring systems to detect unwanted behaviors from API partners and automate enforcement actions.
- Build abuse detection mechanisms and infrastructure.
- Surface abuse patterns to research teams to improve model training.
- Create robust multi-layered defenses for real-time safety mechanisms at scale.
- Analyze user reports of inappropriate content or accounts.
