ML Researcher, Post-training and Safety
Compassion Aligned Machine Learning (CaML)Remote (US)
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.



