Senior Computational Biologist, AI Safety & Bio Risk

Lila Sciences, Inc.; Cambridge, San Francisco (MA, CA); On-site; USD 268,000 - 384,000; Full time

Job summary

Lila Sciences is seeking a Senior / Principal Computational Biologist to join our AI Safety team in Cambridge, MA (also in London and San Francisco). You will conduct original computational biology research for AI safety and build an integrated view of biological risks across LLMs, specialized models, agents and automated laboratories.

You will translate scientific risk judgments into dual-use policy boundaries and mitigation requirements while collaborating with threat modelers, mitigation

Qualifications

• PhD or an equivalent research track with original computational biology work.
• Experience assessing biological dual-use risks and harmful applications.
• Experience applying biology to AI safety, threat modeling or red-teaming.
• Ability to translate findings into actionable safety guidance.

Responsibilities

• Formulate and pursue original computational biology research questions for safety.
• Build an integrated view of risks across LLMs, specialized models, agents and labs.
• Judge biological feasibility and significance of emerging capabilities for misuse.
• Identify gaps and frame questions for external specialists and collaboration.
• Translate risk judgments into dual-use policy boundaries and mitigation needs.
• Collaborate with threat modelers, automated-safety researchers and engineers on evaluations.

Skills

PhD in computational biology

Biological dual-use risk assessment

AI safety research integration

Quantitative analysis

Scientific programming

Cross-functional collaboration

Education

PhD or equivalent experience

Job description

Lila Sciences is seeking a Senior / Principal Computational Biologist to join our AI Safety team in Cambridge, MA (also in London and San Francisco). You will conduct original computational biology research for AI safety and build an integrated view of biological risks across LLMs, specialized models, agents and automated laboratories.

You will translate scientific risk judgments into dual-use policy boundaries and mitigation requirements while collaborating with threat modelers, mitigation