Staff / Principal Security Engineer, AI Safety and Security

Lila Sciences • Cambridge, MA

9h • $192,000 - $306,000

About The Position

Lila Sciences is hiring an experienced security practitioner to lead work at the intersection of AI safety and security. The role investigates how AI systems for scientific discovery could be misused or compromised, identifies which protections matter for specific capabilities and deployments, and evaluates whether those protections work together. The work addresses both dangerous misuse and the protection of sensitive models, data, and research.

The engineer will combine technical investigation, threat modeling, adversarial testing, and clear analysis and writing. They will work closely with the Security team, researchers, and engineers to convert findings into implemented improvements. The position is an opportunity to shape an emerging area of AI safety through security practice. Prior AI safety experience is welcome but not required.

Requirements

• 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 response.
• Ability to reason across security disciplines and identify when specialist judgment is needed.
• A record of resolving consequential security problems, including investigating ambiguous risks, challenging designs, and following improvements through validation across multiple teams.
• Strong technical judgment and ability to examine unfamiliar systems, scrutinize code and configurations where relevant, and use investigation or testing to distinguish plausible claims from demonstrated protections.
• Curiosity about AI safety and scientific systems, ability to learn unfamiliar domains quickly, and careful reasoning when evidence is incomplete.
• Clear writing and effective collaboration, including the ability to explain technical arguments, work through disagreements with specialists, and make actionable recommendations.

Nice To Haves

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

Responsibilities

• Threat-model consequential systems and capabilities across models, deployed services, and scientific workflows, identifying actors, access routes, failure paths, and protections.
• Examine architectures, code, configurations, and operational evidence; run focused adversarial tests, build prototypes, and investigate weaknesses and shared dependencies among protections.
• Translate dangerous-capability assessments into concrete security requirements and assess how compromise of models, sensitive assets, or supporting systems changes safety assessments.
• Define evidence needed to demonstrate that controls and safeguards work together; combine model-evaluation and security-testing findings, explain uncertainty, and recommend improvements or conditions for use.
• Work with Security, Safety, and engineering owners to prioritize changes, specify acceptance criteria, and verify results.
• Identify when changes in system capability, access, or deployment call for stronger protections; plan security work with long lead times and update assessments as systems or evidence change.
• Develop threat models, assessment methods, and technical guidance that colleagues can apply to new problems, and build shared understanding of evidence behind decisions.
• Draw on personnel, physical, and other security specialists where relevant.

Benefits

• Competitive base compensation with bonus potential and generous early-stage equity.
• For full-time U.S. employees: medical, dental, and vision coverage.
• For full-time U.S. employees: employer-paid life and disability insurance.
• For full-time U.S. employees: flexible time off and generous company-wide holidays.
• For full-time U.S. employees: paid parental leave.
• For full-time U.S. employees: educational assistance program.
• For full-time U.S. employees: commuter benefits, including bike share memberships for office-based employees.
• For full-time U.S. employees: company-subsidized lunch program.
• For full-time employees outside the U.S.: a comprehensive benefits program tailored to their region.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed