The Effective Altruism
Opportunities Board
Work on the world's most pressing problems. Browse jobs, fellowships, internships, courses, and more at high-impact organisations.
Software Engineer, Safeguards Evaluations
AnthropicSan Francisco, CA | New York City, NY
San Francisco, CA | New York City, NY
Today
Routes to impact
Direct high impact on an important cause
Skill-building & building career capital
Description
Build evaluation systems that measure and improve AI-powered safety investigations and abuse detection.
- Design evaluation frameworks for agentic monitoring systems
- Build datasets covering cyber, biosecurity, and influence threats
- Analyze performance, robustness, and measurement gaps
- Productionize evaluations for model and system releases
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Machine Learning Engineer
10a LabsRemote (US)
Remote (US)
6 days ago
Senior Software Engineer, AI Security
Carnegie Mellon UniversityArlington, VA / Pittsburgh, PA
Arlington, VA / Pittsburgh, PA
2 weeks ago
Software Engineer, AI Security
Carnegie Mellon UniversityPittsburgh, PA / Arlington, VA
Pittsburgh, PA / Arlington, VA
2 weeks ago
Machine Learning Researcher
Gray SwanRemote
Remote
2 weeks ago
Associate Machine Learning Engineer, Secure AI Lab
Carnegie Mellon UniversityPittsburgh, USA / Arlington, USA
Pittsburgh, USA / Arlington, USA
1 month ago
AI Security Research Engineer
0LabsRemote
Remote
1 month ago
Applied Researcher (Product)
Apollo ResearchLondon, United Kingdom
London, United Kingdom
3 months ago
Security Engineer, Threat Intelligence
AnthropicSan Francisco, USA / New York, USA / Washington, USA / Remote (USA)
San Francisco, USA / New York, USA / Washington, USA / Remote (USA)
1 month ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities