Safety and security

AI control, monitoring and containment

AI control, monitoring and containment is the work of reducing harm when a model's behaviour may be untrusted or adversarial. Companies need it because capable models and agents now act in real systems, and good intentions in training are not a safeguard.

Models are being given tools, code execution and network access, and teams cannot always verify what they will do with them. So founders want controls that hold even if a model is misaligned. The hires are tricky because the field is young and titles vary. Strong candidates usually come from security engineering, formal methods or safety evaluation. Look for people who test controls against realistic adversaries and are honest about residual risk.

Emerging 5

Roles in this family

5 roles

EmergingAI Control ResearcherAn AI Control Researcher designs the safeguards that limit what a model can do if it turns out to be unreliable or hostile. They keep risk bounded…EmergingAgent Containment EngineerAn Agent Containment Engineer builds the boundaries that keep AI agents from doing harm, even if the model misbehaves or is attacked. They matter…EmergingAI Monitor Evaluation EngineerAn AI Monitor Evaluation Engineer tests whether the systems that watch model behaviour actually catch dangerous or unauthorised actions. It matters…EmergingAI Shutdown and Recovery EngineerAn AI Shutdown and Recovery Engineer builds and tests the ways to stop an AI system mid-action and bring it back to a known good state. It matters…EmergingAI Control EngineerAn AI Control Engineer builds the monitoring, sandboxing and containment that let a company use powerful models safely, even if a model is…

Where the people come from

Security engineering, formal methods or AI safety evaluation

Not to be confused with. Controls must be assessed against realistic adversaries and residual risk.

Core skills

  • Formal verification
  • Security engineering
  • Model evaluation
  • AI control

Where it is used

  • Cross-sector AI platforms
  • Cybersecurity
  • Frontier AI governance

Routes in and out

People move in from

People move on to

More in Safety and security

Capability evaluation and benchmarking0 rolesAlignment and scalable oversight0 rolesInterpretability and model internals0 rolesAI application security and misuse defence0 rolesAI robustness, safety engineering and incidents0 roles

← All new job families

Start a search

Hiring in aI control, monitoring and containment?

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