You will conduct adversarial red-teaming of Generative AI models to identify vulnerabilities related to CBRNE threats and critical infrastructure. This involves designing sophisticated attack scenarios and documenting failure modes to strengthen model safety guardrails.
You will conduct adversarial red-teaming of Generative AI models to identify vulnerabilities and safeguard bypasses related to cyber-CBRNE threats. This involves designing complex attack scenarios and documenting failure modes to strengthen model resilience against high-consequence risks.
As a CTI Specialist, you will conduct in-depth investigations to detect and mitigate online threats across various platforms. Your role will involve analyzing patterns, monitoring threat communities, and preparing structured reports with actionable recommendations.
As a CBRN expert, you will write domain-specific prompts and evaluate AI-generated responses to ensure safety and integrity. You will also identify vulnerabilities and provide feedback to improve content generation.
As an OSINT/WEBINT Researcher, you will conduct in-depth research to identify and assess online threats across various platforms. Your work will support the safety of major digital platforms by analyzing data and preparing reports on key findings.
As a Security Red Team Specialist, you will conduct analysis and testing of generative AI systems to enhance their security and integrity. Your role includes performing simulated cyber attacks, vulnerability assessments, and collaborating on mitigation strategies.
The freelancer will be responsible for reviewing GenAI prompts related to CBRN biology. This role requires expertise in the field to ensure the quality and accuracy of the prompts.
Conduct OSINT/WEBINT investigations on illicit online communities and analyze emerging cyber threats. Turn raw intelligence into actionable insights that drive real impact.
The Red Team Specialist will conduct simulated cyber attacks on generative AI models to uncover vulnerabilities and assess risks. They will collaborate with teams to develop strategies for risk mitigation and maintain documentation of findings.
The role involves conducting end-to-end intelligence research projects across various abuse areas, including hate speech and child safety. Analysts will collect and analyze data from diverse sources and prepare reports summarizing key findings.
The role involves producing high-quality, diverse prompt sets that reflect global linguistic and cultural nuances. Additionally, it requires researching online behaviors of threat actors to inform realistic prompt design across multiple policy areas.
