AI Red Teamer, CBRNE

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an AI Red Teamer, CBRNE based in the United States.

This contract role sits at the intersection of advanced AI safety, adversarial testing, and national security.
You will apply deep expertise in a CBRNE discipline to evaluate how AI models respond to sensitive and dual-use requests.
The role focuses on identifying weaknesses in model safeguards and determining whether outputs could provide meaningful real-world harmful uplift.
You’ll design sophisticated evaluation scenarios, assess model responses, and document technical risks with precision.
Your findings will help AI researchers and policy teams strengthen safeguards before vulnerabilities can be exploited.
The environment is highly collaborative, intellectually demanding, and grounded in rigorous ethical and operational standards.
This is an opportunity to apply specialized scientific or technical expertise to an emerging and consequential area of AI security.