About the Role
Security Level 5 is a Bay Area AI security nonprofit dedicated to defending frontier models against nation-state threats. We are building the first datacenter purpose-built to the SL5 standard, designed to protect against adversaries with nation-state resources and billion-dollar budgets. This role is critical in designing and implementing the security architectures and reference tech stack for these advanced AI workloads.
Responsibilities
- Designing and operationalizing network architecture, machine, physical, personnel, or supply chain security for an SL5 datacenter
- Threat modeling AI training infrastructure against nation-state adversaries
- Red-teaming critical AI infrastructure
- Designing and running experiments to assess productivity impacts of SL5 on frontier AI workloads
- Building custom security tooling for SL5 requirements
- Co-developing standards with labs and government stakeholders
- Publishing research for technical and policy audiences
Requirements
- 5+ years in infrastructure security engineering, security research, threat intelligence, or red-teaming
- 2+ years building and stress-testing training infrastructure at a frontier AI lab
- Shipped or compromised production systems and understand the difference between a clean design and one that passed review
- Ability to think like a state-level adversary
- Clear communication with technical and non-technical stakeholders
- Desire for security work to have impact outside the company
Skills
- Infrastructure security engineering
- Security research
- Threat intelligence
- Red-teaming
- AI training infrastructure
- Nation-state adversary thinking
- Technical and non-technical communication
- Performance-optimized frontier AI training and inference infrastructure (SOTA)
- Offensive or defensive nation state operations
- Building datacenters at 100MW+ scale
Location
- Bay Area
Work Type
- In-person
Experience Level
- 5+ years
- 2+ years
Salary/Compensations
- $200,000 - $350,000 USD per year
Benefits
- Full benefits, including healthcare, dental, vision, 401k match, and more
About the Company
- Security Level 5 is a Bay Area AI security nonprofit working with AI labs and US intelligence agencies to defend frontier models from priority nation-state-level threats.
- We are a small technical team, moving fast and growing quickly.
- We wrote the first version of the SL5 standard with input from CISOs, senior security staff at frontier labs, and US security and intelligence officials.
- We are designing SL5 architectures purpose-built for frontier AI workloads and standing up the reference tech stack to guide labs' buildouts.
