Opportunity type
Internship
Cause areas
AI safety & policy
Routes to impact
Skill-building & building career capital
Learning about important cause areas
Testing your fit for a certain career path
Direct high impact on an important cause
Relevant aptitudes
Conceptual & empirical research
Location
Amsterdam, Netherlands
Description
The Existential Risk Observatory is offering a paid research internship in Amsterdam focused on evaluating AI models for dangerous capabilities and alignment.
- Conduct and reproduce AI model evaluations using public open-source datasets, then apply these evaluations to new models and publish your findings.
- Opportunity to deepen research into evaluation sets and contribute to the development of new benchmarks in collaboration with field experts.
- Hybrid work setup: two days onsite in a central Amsterdam office, two days remote; part-time options available.
- Build expertise in a fast-growing field, publish a paper, and expand your professional network.
Visa requirements are not specified in the source.
This text was generated by AI. If you notice any inconsistencies, please let us know using https://airtable.com/appngKrXQ99QHsAo4/shrrnPHkHnhTQNA4u
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities