Counterweight Labs

The role

Turn deep security knowledge into tasks that test what frontier models can actually do. You will build evaluation scenarios, investigate agent behavior, and contribute to hands-on security engagements with our clients. The work spans offensive and defensive security; bring depth in your area and the curiosity to explore unfamiliar systems.

What you’ll work on

  • Design cyber evaluation scenarios with realistic starting access, clear objectives, and meaningful operational constraints.
  • Build reference solutions and independent graders that distinguish genuine success from shortcuts and measurement errors.
  • Run experiments with AI agents, investigate failures, and document what the evidence establishes.
  • Work with engineers to make environments isolated, reproducible, and reliable across repeated runs.
  • Contribute to application security reviews, penetration tests, and research that informs our products and client work.

What you’ll bring

  • Deep hands-on experience in offensive research, application security, cloud and identity security, detection, incident response, or recovery.
  • Programming and scripting skills to build tools, automate workflows, and debug complex systems.
  • Careful experimental judgment and the ability to challenge a flawed metric or assumption.
  • Clear technical writing and evidence of work you can discuss in depth.

Compensation & benefits

The annual base salary range for this role is $180,000–$250,000 USD.

This is a remote role with equity, healthcare, and other benefits. We’ll discuss the compensation package and benefit details with you during the hiring process.

How to apply

Email a short introduction and your résumé or profile to careers@counterweightlabs.com. Put Member of Technical Staff (Security Researcher) in the subject line. A project, research write-up, or other example of your work is welcome; please only share material you’re authorized to share.