Security Researcher (Agentic AI)

TL;DR

Security Researcher (Agentic AI): Identifying and mitigating security threats posed by advanced internal AI agents with an accent on infrastructure security and threat modeling. Focus on designing security controls, stress-testing defenses through penetration testing, and evaluating AI agent capabilities to prevent unauthorized system compromise.

Location: Must be based in San Francisco

Salary: $293,000 – $405,000

Company

hirify.global is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.

What you will do

• Identify potential attack vectors where future internal AI agents could compromise internal systems.
• Design and implement long-lead security controls to mitigate extreme AI-driven threats.
• Conduct stress tests and penetration tests on defenses using AI agent evaluations.
• Collaborate with internal stakeholders to set and achieve security mitigation targets.
• Build prototypes to validate security measures and infrastructure resilience.

Requirements

• Deep technical expertise in security and modern infrastructure.
• Strong software engineering skills with experience building prototypes.
• Proficiency in operating systems, cloud environments, containers, CI/CD, and distributed systems.
• Ability to effectively engage with stakeholders across the organization.
• Must be based in San Francisco.

Nice to have

• Experience securing cloud infrastructure.
• Deep familiarity with core components of the AI stack.

Culture & Benefits

• Work on urgent, high-impact safety research with global implications.
• Collaborate in a fast-paced, mission-driven environment.
• Comprehensive benefits package including equity.
• Commitment to diversity, equity, and inclusion.