GenAI CBRNE Cyber Security Expert

Location: Remote; must be based in the United States or United Kingdom and authorized to work in the US; excluding Illinois and Texas

Salary: $150K–$178K per year, varying based on experience

Company

hirify.global is a trust, safety, and security company providing AI lifecycle protection, including model evaluations, red-teaming, runtime guardrails, and drift detection.

What you will do

• Red-team GenAI models across SCADA, ICS/OT, industrial hacking, critical infrastructure, and CBRNE scenarios.
• Design adversarial prompts, jailbreaks, and multi-turn evaluations involving PLCs, DCS, Modbus, DNP3, IEC 60870-5-104, and Ethernet/IP.
• Evaluate whether models can generate attack payloads, exploit ladder logic, support reconnaissance, or combine benign inputs into high-risk workflows.
• Document failure modes, classify severity, and report findings and mitigations to safety and alignment teams.
• Build repeatable test suites, adversarial datasets, benchmarks, and risk taxonomies.
• Track GenAI attack techniques and CBRNE and critical-infrastructure threats.

Requirements

• Must be US-based and authorized to work, excluding Illinois and Texas.
• Advanced degree in cybersecurity, computer science, engineering, security studies, CBRNE sciences, or a related field, or equivalent professional, military, or government experience.
• Deep industrial cybersecurity expertise covering SCADA, ICS/OT, industrial protocols, PLCs, and cyber-physical attack chains.
• Strong CBRNE knowledge, particularly its intersection with cyber and digital systems.
• Experience in red teaming, penetration testing, adversarial simulation, vulnerability research, or offensive security.
• Experience or aptitude in GenAI red teaming, adversarial prompts, jailbreak research, multi-turn testing, and LLM safety evaluation, plus strong technical writing skills.

Nice to have

• Hands-on LLM red teaming, AI safety evaluations, or jailbreak and prompt research.
• Experience building red-team test cases, datasets, benchmarks, or evaluation pipelines.
• Knowledge of frontier AI safety, dangerous-capability evaluations, responsible scaling frameworks, MITRE ATT&CK, NIST, or IEC 62443.
• Background in offensive security, threat intelligence, incident response, adversary emulation, national security, defense, intelligence, or high-consequence industrial environments.
• Offensive-security or ICS/OT certifications and expertise in chemical, biological, radiological, nuclear, or cyber-physical risk.

Culture & Benefits

• Remote work arrangement.
• Work focused on safeguarding AI systems and communicative technologies.
• Projects supporting frontier model labs, enterprises, and user-generated-content platforms.
• Exposure to AI security, industrial cybersecurity, critical infrastructure, and high-consequence threat analysis.