JobInterpretabilityEmpiricalSenior
Research Scientist, Interpretability
Meridian Alignment Lab
Berkeley, CA · Hybrid $180k–$240k Rolling
Lead an interpretability agenda from hypothesis to publishable result, with a small team and real compute.
What you'd do
- Own a research direction on feature-level model auditing
- Mentor two junior researchers and one resident
- Publish negative results as readily as positive ones
What they look for
- Track record of empirical ML research
- Comfort with large-scale training and analysis code
- Ability to state what would falsify your agenda
Meridian Alignment Lab
Small empirical lab studying whether oversight methods hold up when the model is smarter than the overseer.
Research lab · 12 people · Philanthropically funded through 2028