Safety and security

Alignment and scalable oversight

Alignment and scalable oversight is research into getting models to behave as intended, and into supervising them when the work is hard to judge. AI companies need it so that capable systems stay useful, predictable and open to correction.

As models take on tasks that people cannot easily check by eye, supervision becomes a research problem rather than a routine step. Companies want people who can improve behaviour and test whether the improvement holds. The hiring is tricky because the titles blur. A good candidate keeps clear the difference between behaviour that looks aligned and what a model is actually optimising for, and says so plainly.

Hiring now 3Emerging 1

Roles in this family

4 roles

Hiring nowScalable Oversight ResearcherA scalable oversight researcher designs and tests ways to supervise AI systems on tasks too hard for a person to judge easily. The work shows…EmergingReward Hacking ResearcherA Reward Hacking Researcher finds and studies cases where models exploit the reward or evaluation signal instead of doing the intended task, then…Hiring nowModel Behaviour ResearcherA Model Behaviour Researcher studies how a model's behaviour shifts across contexts and training, and shows what caused the shift. That gives the…Hiring nowModel Behaviour and Character DesignerA Model Behaviour and Character Designer defines and tunes how a model reasons, communicates and handles values trade-offs. They make the product's…

Where the people come from

ML research, preference learning or technical safety research

Not to be confused with. A behaviorally aligned result is not proof of internal objectives.

Core skills

  • Experimental design
  • Preference learning
  • Model evaluation
  • Alignment research

Where it is used

  • Cross-sector AI platforms
  • Frontier AI governance

Routes in and out

People move in from

More in Safety and security

Capability evaluation and benchmarking0 rolesInterpretability and model internals0 rolesAI control, monitoring and containment0 rolesAI application security and misuse defence0 rolesAI robustness, safety engineering and incidents0 roles

← All new job families

Start a search

Hiring in alignment and scalable oversight?

Tell us the work you need done. We find the people already doing it, whatever their job title says.