SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 268,000 - 384,000 / annual
Lila Sciences is building Scientific Superintelligence to solve major scientific challenges through advanced AI models and proprietary AI Science Factory instruments. The company is assembling a talent-dense AI safety team to identify and mitigate risks from scientific superintelligence while preserving core scientific discovery capabilities.
You will serve as a materials scientist focused on mapping dual-use risks across the materials sciences domain. Your role bridges deep materials expertise with risk assessment to safeguard increasingly capable scientific AI systems.
Key responsibilities include:
- Map misuse risks by connecting material properties, processing, and functional performance across 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 expertise gaps, commission targeted scientific input with the expert-program team, and integrate specialist findings into a coherent risk landscape assessment
- Translate dual-use judgments into policy boundaries, evaluation priorities, and mitigation requirements that support beneficial materials research
- Collaborate with threat modelers, evaluation researchers, engineering and experimental colleagues to assess capabilities, interpret red-team findings, and evaluate safeguards
You will work across science, model training, and lab integration teams to develop and implement a bespoke safety strategy tailored to Lila's specific goals and deployment strategies. The role involves technical safety strategy development, broader ecosystem engagement, safety-focused evaluations, safety systems design, and research into longer-term needs such as oversight of superintelligent scientific systems.
REQUIREMENTS:
- PhD or comparable experience in materials science or closely related discipline, with strong grasp of relationships between structure, properties, processing, and applications. Relevant backgrounds include particulate, porous and formulated systems; structural and functional materials including thin films, electrochemical materials, metals and alloys
- Substantive experience assessing dual-use risks in a relevant area, with 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, with ability to investigate risks beyond immediate specialism
- Ability to identify appropriate specialists, evaluate technical evidence, and synthesize contributions across scientific and security disciplines
- Clear scientific communication, independent research judgment, and ability to collaborate across science, engineering, and policy
BONUS:
- Prior experience applying materials or related physical-science expertise to AI safety through threat analysis, evaluations, 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
