Senior Cyber Researcher - Frontier AI Security

Enclosure; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Enclosure is a security lab focused on preventing sabotage, escape, and theft of ASI. We seek a cyber researcher to own a significant portion of our cyber research as an IC and advance offensive security capabilities.

You will work on vulnerability research, exploit development, Linux security internals, EDR evasion, and AI-system red teaming within a frontier AI security context. Strong curiosity and self-directed work are prized.

Qualifications

• Experience in offensive security, red teaming or computer network exploitation.
• Vulnerability research and exploit development experience.
• Knowledge of Linux security internals, EDR tooling and evasion techniques.
• Proficiency in network explorations and exploitation.
• Experience with offensive security tooling and frameworks such as Kali, Metasploit and Burp Suite.
• MDAR incidents handling experience across types of incidents.
• AI-system red teaming or autonomous cyber evaluation experience.
• Reverse engineering, malware analysis or low-level systems work.

Responsibilities

• Own a significant part of our cyber research as an IC.
• Contribute to offensive security assessments and tooling development.
• Engage in threat modeling, vulnerability discovery and exploitation research.
• Collaborate with frontier AI security and infrastructure teams to improve defenses.

Skills

Offensive security

Vulnerability research

Linux security

Network exploitation

Penetration testing tooling

MDR experience

AI-system red teaming

Reverse engineering

Tools

Kali

Metasploit

Burp Suite

XBOW

Job description

Enclosure is a security lab focused on preventing sabotage, escape, and theft of ASI. We seek a cyber researcher to own a significant portion of our cyber research as an IC and advance offensive security capabilities.

You will work on vulnerability research, exploit development, Linux security internals, EDR evasion, and AI-system red teaming within a frontier AI security context. Strong curiosity and self-directed work are prized.