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, Value Persistence Through Reinforcement Learning
Today
Routes to impact
Direct high impact on an important cause
Description
Research engineering role studying whether values instilled during AI midtraining persist through subsequent reinforcement learning.
- Build and debug end-to-end midtraining and RL pipelines
- Generate and validate synthetic training corpora and controls
- Run evaluations and interpretability methods on trained models
- Contribute to open-source releases, checkpoints, and research papers
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
PhD Position, Responsible Machine Learning
ELLIS Institute TübingenVienna, Austria
Vienna, Austria
Today
Research Engineer / Research Scientist, Control Red Team
AI Security Institute (AISI)London, UK
London, UK
5 days ago
Research Engineer / Research Scientist, Misuse Red Team
AI Security Institute (AISI)London, UK
London, UK
5 days ago
Research Scientist, Control
Apollo ResearchSan Francisco, CA / London, UK
San Francisco, CA / London, UK
5 days ago
Founding Member of Technical Staff
Sampura ResearchLondon, UK
London, UK
6 days ago
Head of Evaluations, AI Red Teaming
Trajectory LabsBerkeley, CA
Berkeley, CA
1 week ago
Senior Data Scientist, Safety
FacultyLondon, UK
London, UK
1 week ago
Research Scientist, Member of Technical Staff
AI DigestRemote
Remote
1 week ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities