The Effective Altruism
Opportunities Board
Work on the world's most pressing problems. Browse jobs, fellowships, internships, courses, and more at high-impact organisations.
Research Engineer / Research Scientist, Alignment Red Team
AI Security Institute (AISI)London, UK
London, UK
Today
Deadline
2026-10-11
Routes to impact
Direct high impact on an important cause
Description
Research engineering and research science roles detecting and evaluating misalignment in frontier AI systems.
- Develop novel methods to automatically search for misalignment in frontier models
- Run pre-deployment alignment evaluations and report findings to AI companies and governments
- Build open-source tooling for more efficient, realistic alignment evaluations
- Pre-release access to multiple frontier models and ample compute
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Research Scientist, Agent Robustness
ScaleSan Francisco, CA / New York, NY
San Francisco, CA / New York, NY
2 weeks ago
Member of Technical Staff, Embedded Assessments
Model Evaluation & Threat Research (METR)Berkeley, CA
Berkeley, CA
2 weeks ago
Research Scientist
GoodfireLondon, UK
London, UK
1 month ago
Research Engineer, Scalable Interpretability
TransluceSan Francisco, CA
San Francisco, CA
2 months ago
Machine Learning Manager
LawZeroMontreal, Canada
Montreal, Canada
2 months ago
Research Engineer, Human Influence
AI Security Institute (AISI)London, UK
London, UK
Today
Engineering Lead, Chem Bio
AI Security Institute (AISI)London, UK
London, UK
6 days ago
Expression of Interest, Cyber and Autonomous Systems Team
AI Security Institute (AISI)London, UK
London, UK
1 month ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities