Member of Technical Staff - Multiple Teams

About Security Level 5

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're a small technical team, we move fast, and we're growing quickly this year.

The Mission

We're hiring for what's plausibly the most difficult, urgent, and interesting challenge in AI security engineering this decade (for humans, at least): designing and building the first datacenter purpose-built to Security Level 5, the standard for defending frontier AI labs against attackers with the resources of a nation-state and billion-dollar budgets. We're working on the first SL5 components this year and aiming for an at-scale SL5 datacenter build in 2027.

We wrote the first version of the standard with input from CISOs and senior security staff at the frontier labs, and US security and intelligence officials. Now we're designing the SL5 architectures purpose-built for frontier AI workloads, and standing up the reference tech stack to guide labs' buildouts. This stack has to hold against nation-states, not destroy researchers' productivity, not cost more than labs can pay, and ship in 2-3 years.

About the role

What you'd work on

• Designing and operationalizing the network architecture, machine, physical, personnel, or supply chain security needed to implement 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

You'd be a fit if you

• Have 5+ years in one of: infrastructure security engineering, security research, threat intelligence, or red-teaming

• Or have 2+ years building and stress-testing training infrastructure at a frontier AI lab. We've seen people without these credentials succeed at some of our most difficult tasks, so if that's you, let us know why you'll succeed at the role anyways.

• Have shipped or compromised production systems and know the difference between a clean design and one that just passed review

• Think like a state-level adversary, whether you express that in writing, in architecture, or in code

• Communicate clearly with both technical and non-technical stakeholders

• Want your security work to matter outside the company shipping it

Bonus

• Familiarity with SOTA of performance-optimized frontier AI training and inference infrastructure (as a maintainer or researcher having used it)

• Experience with offensive or defensive nation state operations

• Experience building datacenters at 100MW+ scale

Logistics

Bay Area, in-person. This role's base salary range is $200,000 - $350,000 USD per year. We may be open to paying exceptional and/or highly experienced employees more than this. We also provide full benefits, including healthcare, dental, vision, 401k match, and more. Engineers, researchers, and hybrids: apply even if your background isn't a clean match. We'll figure out the right fit.