Principal Product Manager (AI Model Security)

TL;DR

Principal Product Manager (AI Model Security): Owning the security hardening strategy for frontier models to make them resilient against adversarial attacks and purpose-built for security practitioners with an accent on LLM security threats and red-teaming frameworks. Focus on designing evaluation benchmarks, mitigating zero-day exploit risks, and aligning model capabilities with real-world security workflows.

Location: Mountain View, United States (Hybrid: must be in office at least 4 days a week)

Salary: $188,000 – $304,200

Company

hirify.global AI’s Superintelligence Team (MAIST) is a startup-like unit within hirify.global dedicated to creating ultra-capable AI systems that remain controllable, safety-aligned, and anchored to human values.

What you will do

• Define and prioritize the security hardening strategy for frontier models across the OWASP LLM threat surface.
• Evaluate and mitigate risks of models being used to generate zero-day exploits, malware, or novel attack vectors.
• Design and iterate adversarial testing programs and red-teaming frameworks, both automated and human-driven.
• Partner with Azure Security and Security Copilot teams to translate product requirements into model training priorities.
• Build benchmark suites and evaluation frameworks to measure real-world security usefulness for practitioners.
• Establish security criteria for model launches and influence model training, fine-tuning, and RLHF.

Requirements

• Bachelor’s Degree and 5+ years of experience in product management, security engineering, or software development.
• Hands-on experience building, evaluating, or shipping ML-powered products or security tools.
• Deep familiarity with LLM security threats including prompt injection, jailbreaking, and data exfiltration.
• Proven track record of building evaluation systems, security benchmarks, or adversarial testing frameworks.
• Must be based in or able to work from the Mountain View office at least four days a week.

Nice to have

• Postgraduate degree in Computer Science, Security, or AI/ML.
• Experience in offensive security, penetration testing, or red teaming applied to AI systems.
• Familiarity with security tooling such as SIEM, SOAR, EDR, and threat intelligence platforms.
• Understanding of the model lifecycle from pre-training and RLHF to deployment and monitoring.
• Previous experience working within enterprise security organizations.

Culture & Benefits

• Startup-like environment with high ownership and direct accountability for production outcomes.
• Collaborative culture based on a growth mindset, respect, integrity, and accountability.
• Opportunity to work on the frontier of AI Superintelligence and shape the security of global-scale models.
• Comprehensive corporate benefits provided by hirify.global.