Senior​/Principal Research Scientist, AI Safety, Biological​/Physical Sciences

Your Impact at LILA

We’re building a talent-dense, high-agency AI safety team at Lila that will engage all core teams within the organization (science, model training, lab integration, etc.), to prepare for risks from scientific superintelligence. The initial focus of this team will be to build and implement a bespoke safety strategy for Lila, tailored to its specific goals and deployment strategies. This will involve technical safety strategy development, broader ecosystem engagement, as well as developing technical collateral including risk- and capability-focused evaluations and safeguards.

• Set the build and research strategy for Lila’s safety approach to biological / physical risks.
• Design and build capability evaluations to test for scientific risks (both known but especially novel) from cutting edge scientific models integrated with automated physical labs, across biological / physical sciences.
• Coordinate and lead threat modelling exercises with internal and external scientific experts, including monitoring for emerging technologies and use-cases.
• Develop and curate high-quality training and test data for evals and safety systems.
• Evaluate risks from Lila’s capabilities, including through interactions with the wider ecosystem of capabilities (e.g. general-purpose frontier models as well as narrow scientific tools)
• Contributing to broader, high-quality research efforts - as and when needed - for scientific capability evaluation and restriction.
• Contribute to external communications on Lila’s safety efforts.

• A PhD in either a biological sciences domain (e.g., molecular biology, virology, computational biology or related fields) or a physical sciences domain (materials sciences, physics, chemistry, chemical or nuclear engineering, or related fields), or other related experience.
• Demonstrated ability to set research directions for open problems in dual-use risks in the biological / physical sciences.
• Experience in scientific computing, across either biological or physical sciences.
• Familiarity with dual-use research and dissemination concerns, across the relevant safety / regulatory / governance frameworks (e.g. export control frameworks, biological and chemical-related conventions and controls).
• Ability to communicate complex technical concepts and concerns to non-expert audiences effectively.
• Demonstrated ability to lead teams of internal and external collaborators in buildout of Lila’s point-of-view on biological / physical risks
• Demonstrated ability to deal with cross-functional stakeholders (science, AI, product, policy) in a complex environment.

• Experience in developing or applying ML to biological or physical sciences
• Experience in building evaluations, or conducting red‑teaming exercises, across scientific risks for frontier models / narrow scientific tools.

• This position may be based in any of Lila’s offices, including Cambridge (MA), San Francisco (CA), or London (UK).

We offer competitive base compensation with bonus potential and generous early‑stage equity. Your final offer will reflect your background, expertise, and expected impact.

Full-time U.S. employees receive a comprehensive benefits program including medical, dental, and vision coverage; employer-paid life and disability insurance; flexible time off with generous company-wide holidays; paid parental leave; an educational assistance program; commuter benefits, including bike share memberships for office-based employees; and a company subsidized lunch program.

Full-time employees outside the U.S. receive a comprehensive benefits program tailored to their region. USD salary ranges apply only to U.S.

-based positions; international salaries are set to local market.

Expected Base Salary Range

$268,000—$384,000 USD

Lila Sciences is building Scientific Superintelligence to solve humankind’s greatest challenges. We believe science is the most inspiring frontier for AI. Rather than hard-coding expert knowledge into tools, LILA builds systems that can learn for themselves.

LILA combines advanced AI models with…