- In this role, you'll design and implement solutions to ensure AI systems follow human intent, even in complex scenarios.
- Develop alignment capabilities for subjective, context-dependent challenges.
- Design evaluations to measure AI risks and alignment with human values.
- Build tools to study model robustness and how alignment scales with increased capabilities.
- Create human-AI interaction methods that improve how people supervise and control AI systems.
#J-18808-Ljbffr
We are looking to fill the Researcher, Alignment position at Safety Talent in San Francisco, CA, United States.
We have an opening for a Researcher, Alignment in San Francisco, CA, United States within IT & Technology.
This role, Researcher, Alignment at Safety Talent, could be your next career step.
Are you ready to take on the Researcher, Alignment role at Safety Talent?
We would love to welcome a new Researcher, Alignment to our group in San Francisco, CA, United States.