Director, AI Alignment and Interpretability (Remote)

As a Security-domain AI Researcher at CrowdStrike, you will lead alignment and interpretability research for advanced AI systems designed to detect and counter cyber threats. You will develop methods to understand model internals, identify offensive misuse signals, and create evaluation protocols that ensure AI systems behave within intended bounds. This role requires a balance of hands-on technical leadership in mechanistic interpretability with the strategic ability to guide a lean research team.