Staff / Principal Security Engineer, AI Safety and Security

The role

You will lead work at the boundary between AI safety and security by investigating real systems and developing threat models. You will test assumptions, recommend protections for capabilities and deployments, and work with security, safety, and engineering teams to implement improvements.

What you will do

• Threat-model consequential systems and capabilities
• Test the assumptions behind defenses by examining architectures, code, and configurations
• Shape the protections needed for safe deployment
• Make evidence-based recommendations
• Carry findings through to practical improvements
• Anticipate what more capable systems will require
• Develop methods that others can use

Required qualifications

• Substantial hands-on security experience and deep expertise in at least one relevant discipline, such as security architecture, application or infrastructure security, offensive security, or incident
• A record of resolving consequential security problems
• Strong technical judgment
• Curiosity about AI safety and scientific systems
• Clear writing and effective collaboration

Nice to have

• Securing ML infrastructure, model assets, research environments or AI agents
• Evaluating safeguards, adversarial robustness or defenses against sophisticated threats
• Translating risk assessments into technical requirements, assurance evidence or deployment decisions
• Working in scientific or other environments where digital access can have significant real-world consequences
• Prior experience in AI safety

Benefits

• Medical, dental, and vision coverage
• Employer-paid life and disability insurance
• Flexible time off with generous company wide holidays
• Paid parental leave
• Educational assistance program
• Commuter benefits, including bike share memberships for office based employees
• Company subsidized lunch program

About the company

Lila Sciences is building Scientific Superintelligence™ to solve humankind's greatest challenges. The company builds systems that can learn for themselves by combining advanced AI models with proprietary AI Science Factory™ instruments.