Software Engineer, Safeguards
Core
Build safety and oversight mechanisms to monitor AI models, detect misuse, and enforce acceptable use policies.
Role type
Senior IC software engineer (AI safety & abuse detection)
Builds
Real-time monitoring systems, abuse detection infrastructure, and internal dashboards for safety analysts
Domain
AI safety, trust & safety, adversarial input mitigation
Deliverable
production ML models | product features | infrastructure
Required skills
Python, TypeScript, full-stack development, abuse/fraud detection, system design, API security
Preferred skills
AI/ML trust & safety mechanisms, prompt engineering, jailbreak attack mitigation, internal tooling for ops teams
Technologies
Python, TypeScript
Responsibilities
Develop monitoring systems to detect unwanted behaviors from API partners and surface them in dashboards; Build abuse detection mechanisms and infrastructure; Surface abuse patterns to research teams to harden models at training; Build robust multi-layered defenses for real-time safety improvements at scale
Seniority
Senior, hands-on IC
