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 Scientist, Safety Oversight
Google DeepMindMountain View, CA
Mountain View, CA
Today
Routes to impact
Direct high impact on an important cause
Skill-building & building career capital
Description
Monitors the safety and alignment of deployed AI models through large-scale production data analysis.
- Builds classifiers and pipelines to detect model misbehavior and misuse at scale
- Researches cross-context monitoring to catch coordinated harms and novel attack vectors
- Analyzes model activations, actions, and reasoning traces to develop new safety signals
- Collaborates with infrastructure and data teams to scale safety oversight work
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Research Engineer, Human Influence
AI Security Institute (AISI)London, UK
London, UK
5 days ago
Senior Research Scientist, AI Safety Evaluations
FacultyLondon, UK
London, UK
1 month ago
Research Scientist, Manipulation Evaluations
Apart ResearchRemote (Europe preferred)
Remote (Europe preferred)
3 months ago
Research Scientist/Engineer (Science of Scheming)
Apollo ResearchLondon, United Kingdom
London, United Kingdom
6 months ago
Research Scientist/Engineer (Evaluations)
Apollo ResearchLondon, United Kingdom
London, United Kingdom
6 months ago
AI Research Scientist, Safety
Bosch ResearchSunnyvale, CA
Sunnyvale, CA
Today
Postdoctoral Researcher, Centre for Eudaimonia and Human Flourishing
University of OxfordOxford, UK
Oxford, UK
3 days ago
Model Policy Manager, Agentic Safety
OpenAISan Francisco, CA
San Francisco, CA
3 days ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities