Senior Research Scientist / Engineer, Deception
FAR.AIBerkeley, CA preferred / Remote
AI safety & policy
Full-time
AI safety & policy
Full-time
Salary
$225K – $350K
Routes to impact
Direct high impact on an important cause
Description
Lead research on detecting and mitigating AI deception, partnering with the team’s Research Lead to scale methods to a level frontier labs can adopt.
- Lead projects on white-box deception detection, probe-based monitoring and training against probes
- Run post-training and RL experiments on large models, including RLVR and probe-penalty fine-tuning
- Design model organisms that stress-test methods against realistic failure cases
- Mentor Members of Technical Staff and help frontier labs adopt the team’s methods
- Visa sponsorship available for in-person employees
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
