Counterweight Labs

What we do

Research that holds up
in real systems.

Models can find vulnerabilities, investigate intrusions, and act across complex systems. Understanding their capability takes realistic tasks, reliable infrastructure, and evidence of what actually happened.

We build the environments to measure and develop those capabilities. Our public benchmarks explain the tasks and methods; our products support teams evaluating and training their models.

Organizations can engage our world-class researchers for penetration testing, security assessments, and application security consulting. Our AI consulting and integration work helps teams automate business and security processes.

How we work

Measure both sides

Study offensive and defensive capabilities together. Understand what a model can do and where it needs to improve.

Verify the outcome

Check what changed in the system. Make results traceable to evidence, with assumptions and limits stated clearly.

Build for real use

Deliver systems people can operate, experiments they can reproduce, and findings they can act on.

Join the team

Build what comes next.

Remote roles across security research, AI research, software engineering, and infrastructure.

Explore careers