The Effective Altruism
Opportunities Board

Work on the world's most pressing problems. Browse jobs, fellowships, internships, courses, and more at high-impact organisations.
Most of our opportunities are sourced from 80,000 Hours and Probably Good
ML Researcher, Post-training and Safety
ML Researcher, Post-training and Safety
AI safety & policy
Full-time
AI safety & policy
Full-time
Salary
$200,000 to $300,000
Routes to impact
Direct high impact on an important cause
Description
Lead the training side of a research agenda studying how values get into language models and whether they survive later training.
  • Run RL post-training and synthetic-data mid-training on open-weight models
  • Build evals that test whether values hold up under adversarial prompting
  • Study reward hacking, sycophancy and specification gaming
  • Publish findings on arXiv and LessWrong, in a small team with no management layers
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Head of AI Safety and Security Research
Head of AI Safety and Security Research
AliceRamat Gan, Israel
AI safety & policy
Full-time
Senior Research Scientist, AI Biosecurity Assessments
Senior Research Scientist, AI Biosecurity Assessments
SecureBioRemote (US)
Biosecurity & pandemic preparedness
AI safety & policy
Full-time
Threat Modeling Lead, Harmful Manipulation, DeepMind
Threat Modeling Lead, Harmful Manipulation, DeepMind
Google DeepMindNew York, NY / London, UK / Mountain View, CA
AI safety & policy
Full-time
Policy Development, Technical AI Governance
Policy Development, Technical AI Governance
AnthropicSan Francisco, CA / New York, NY / Washington, DC
AI safety & policy
Full-time
AI Chemical Security Researcher
AI Chemical Security Researcher
Concordia AIBeijing, China / Singapore
AI safety & policy
Biosecurity & pandemic preparedness
Full-time
Deadline soon
Research Scientist, Frontier Safety Framework Risk Modelling and Governance
Research Scientist, Frontier Safety Framework Risk Modelling and Governance
Google DeepMindLondon, UK / New York, NY / San Francisco, CA
AI safety & policy
Full-time

Find your next step

Learn about the core ideas of effective altruism
Sign up for a free, structured, 8-week introductory course, where you’ll learn more about effective altruism with a small cohort.
Free
Online
8 weeks
Starting Dec 7
Join the effective altruism newsletter
Monthly ideas, news, and opportunities from across the effective altruism movement, including jobs, events, and courses. Plus a free book when you subscribe.
60k+ subscribers
72 subscribed today
Meet people working on important problems
Join effective altruism conferences to hear from others, explore ideas and career paths, and build connections.