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, Responsible Frontier AI Research
Google DeepMindLondon, UK
London, UK
Today
Routes to impact
Direct high impact on an important cause
Description
Design and scale evaluation frameworks for frontier language models, focusing on detecting harmful manipulation and turning safety research into deployable mitigations.
- Prototype scalable engineering solutions across responsibility research
- Build training and inference pipelines to detect manipulative model behaviors
- Develop post-training mitigations for persuasion, sycophancy, and covert influence risks
- Maintain infrastructure tracking model safety performance across releases
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Research Scientist, Safety Oversight
Google DeepMindMountain View, CA
Mountain View, CA
1 week ago
Research Engineer / Research Scientist, Confidential Computing
Singapore AI Safety Hub (SASH)Remote (UK / Singapore)
Remote (UK / Singapore)
6 days ago
Research Engineer, Human Influence
AI Security Institute (AISI)London, UK
London, UK
1 week ago
Research Engineer, AI Safety and Evals
Andon LabsSan Francisco, CA
San Francisco, CA
1 month ago
Senior Research Scientist, AI Safety Evaluations
FacultyLondon, UK
London, UK
2 months ago
Chief Technology Officer
SyntonyRemote
Remote
2 months ago
Research Scientist / Engineer
SaferAIParis, France / London, UK / San Francisco, CA
Paris, France / London, UK / San Francisco, CA
2 months ago
Doctoral Researchers, Natural Language Processing and AI
Ubiquitous Knowledge Processing (UKP) LabDarmstadt, Germany
Darmstadt, Germany
2 months ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities