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 identify and mitigate risks from scientific superintelligence while retaining the core scientific discovery capabilities of the stack. 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, safety-focused evaluations, safety systems to mitigate risks, and a research agenda that explores longer-term needs such as oversight of superintelligent scientific systems.

We are seeking a chemist to map risk across the chemical sciences domain: you will connect deep chemistry expertise with dual-use risk assessment to help safeguard increasingly capable scientific AI. You will investigate how advances in chemical research could change harmful capabilities, including established and emerging chemical threats.

What You'll Be Building

• Map chemical misuse risks across scientific models, agents and automated experimentation, connecting scientific advances to harmful applications and identifying emerging or overlooked pathways.
• Assess how scientific feasibility, practical complexity and actors' expertise or resources affect the plausibility and likelihood of misuse, including which constraints AI could change.
• Distinguish established capabilities, plausible future developments and weakly supported hypotheses, updating assessments as scientific evidence and AI capabilities evolve.
• Identify gaps in coverage, frame questions for consultants and specialist organizations, and assess and integrate their findings with support from the expert-program team.
• Translate scientific risk judgments into dual-use policy boundaries, evaluation priorities and mitigation requirements that preserve beneficial chemistry.
• Partner with threat modelers, evaluation researchers and mitigation teams to design informative assessments, interpret red-team findings and test safeguards.

What You'll Need to Succeed

• Deep expertise (a PhD, or comparable experience) in synthetic chemistry or a closely related discipline, demonstrated through substantial research or applied work and sound interpretation of experimental evidence. This includes a background in molecular design and medicinal chemistry, inorganic and organometallic chemistry, synthesis, process development and formulations, or other relevant sub-fields.
• Substantive experience assessing chemical dual-use risks (e.g. across national security, export controls, or other chemical risk tracking such as the CWC).
• Strong scientific judgment about feasibility, uncertainty and practical constraints, including the ability to investigate unfamiliar questions and recognize the limits of your expertise.
• The ability to identify appropriate specialists, critically assess their evidence and combine findings across disciplines into defensible risk assessments.
• Clear scientific communication, independent research judgment and an ability to collaborate across science, engineering and policy.

Bonus Points For

• Prior experience applying domain expertise to AI safety through one or more of: scientific analysis informing threat models; evaluation or red-teaming work; or mitigation design.
• Experience commissioning specialist research or coordinating external scientific collaborators.
• Experience with automated chemistry, scientific modeling or the translation of computational findings into physical experiments.