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

What You'll Be Building

• Map misuse risks by connecting material properties, processing and functional performance (across a range of materials domains) to harmful applications, including emerging or overlooked uses of scientific advances.
• Assess how physical feasibility, processing complexity, manufacturing requirements and actors' resources affect the plausibility and likelihood of misuse, including which constraints AI could change.
• Distinguish established capabilities, plausible future developments and weakly supported hypotheses, revising assessments as evidence changes across models, tools and automated laboratories.
• Identify gaps in expertise, commission targeted scientific input with the expert-program team, and integrate specialist findings into a coherent assessment of the risk landscape.
• Translate dual-use judgments into policy boundaries, evaluation priorities and mitigation requirements that support beneficial materials research.
• Work with threat modelers, evaluation researchers and engineering and experimental colleagues to assess capabilities, interpret red-team findings and evaluate safeguards.

What You'll Need to Succeed

• Deep expertise (a PhD, or comparable experience) in materials science or a closely related discipline, with a strong grasp of the relationships between structure, properties, processing and applications. Relevant backgrounds include particulate, porous and formulated systems; and structural and functional materials, including thin films, electrochemical materials and metals and alloys.
• Substantive experience assessing dual-use risks in a relevant area, with a strong understanding of harmful applications such as nuclear proliferation, radiological misuse, weapons-related capabilities (e.g. energetics) or other consequential materials risks.
• Sound judgment about physical possibility, practical feasibility and uncertainty, together with the ability to investigate risks beyond your immediate specialism.
• The ability to identify appropriate specialists, evaluate technical evidence and synthesize contributions across scientific and security disciplines.
• Clear scientific communication, independent research judgment and an ability to collaborate across science, engineering and policy.

Bonus Points For

• Prior experience applying materials or related physical-science expertise to AI safety through one or more of: threat analysis, evaluations or red teaming, or mitigation design.
• Experience commissioning specialist research or assessing emerging technologies across disciplinary boundaries.
• Experience with computational materials science, advanced manufacturing or automated synthesis and characterization.