Senior AI Safety & Security Engineer

Lila Sciences, Inc.; Cambridge, San Francisco (MA, CA); On-site; USD 192,000 - 306,000; Full time

Job summary

Lila Sciences in Cambridge, MA (and London/San Francisco) seeks a Staff/Principal Security Engineer to lead AI safety and security efforts at the boundary of safety and security. You will investigate systems, develop threat models, test assumptions and propose protections for capabilities and deployments.

You will work with Security, Safety and engineering teams to translate findings into implemented improvements, shaping how future AI systems are safeguarded and trusted.

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 response.
• A record of resolving consequential security problems, working with multiple teams to implement improvements.
• Strong technical judgment across unfamiliar systems, code and configurations.
• Curiosity about AI safety and scientific systems, with the ability to learn quickly.
• Clear writing and effective collaboration to turn investigations into actionable recommendations.

Responsibilities

• Threat-model consequential systems and capabilities across models and workflows.
• Test the assumptions behind defenses through focused adversarial tests and code/config reviews.
• Shape protections for safe deployment and assess impact on safety.
• Make evidence-based recommendations and define acceptance criteria.
• Carry findings through to practical improvements with engineering owners.
• Anticipate future needs as systems evolve and scale protections accordingly.
• Develop methods and guidance that others can apply to new problems.

Skills

Security architecture

Application security

Incident response

Offensive security

Analytical judgment

Tools

Threat modeling

Job description

Lila Sciences in Cambridge, MA (and London/San Francisco) seeks a Staff/Principal Security Engineer to lead AI safety and security efforts at the boundary of safety and security. You will investigate systems, develop threat models, test assumptions and propose protections for capabilities and deployments.

You will work with Security, Safety and engineering teams to translate findings into implemented improvements, shaping how future AI systems are safeguarded and trusted.