AI Safety Evaluator: Biosecurity & Synthetic Biology Expert

SaidGig; New York (NY); Remote; USD 69,000 - 124,000; Full time

Job summary

SaidGig is seeking a remote biosecurity contractor to develop evaluation frameworks and realistic threat scenarios for AI systems, focusing on biosafety and public-health impact. The position emphasizes domain expertise over AI experience and requires strong written and verbal communication.

Responsibilities include building a misuse taxonomy, designing safe evaluation scenarios, establishing risk severity, and advising on safety and governance. Independent contractor terms apply.

Qualifications

• 5+ years in biosecurity, biorisk management; 8–20 years for senior roles.
• Advanced degree, certification, or equivalent in biosecurity, synthetic biology, or public health.
• Hands-on roles as biorisk officer, synthetic biology researcher, biodefense specialist, or laboratory director.
• Proven ability to develop threat scenarios and risk taxonomies with domain credibility.
• Excellent written and verbal communication with precise, actionable input.

Responsibilities

• Develop a comprehensive taxonomy of biological misuse scenarios covering current and emerging threats.
• Design safe, realistic evaluation scenarios to test biosafety measures and dual-use risk protocols.
• Establish severity ratings for biological risks to support threat modeling and mitigation.
• Perform rigorous false-negative reviews of draft benchmarks for protective outcomes.
• Advise on laboratory safety protocols, containment strategies, and governance best practices.
• Contribute insights to documentation, scenario development, and cross-functional communication.
• Collaborate with multidisciplinary teams to contextualize misuse risks for public-health impact modeling.

Skills

Biosecurity

Laboratory safety

Biological misuse

Public-health threat modeling

Education

Advanced degree or equivalent in biosecurity/public health

Job description

SaidGig is seeking a remote biosecurity contractor to develop evaluation frameworks and realistic threat scenarios for AI systems, focusing on biosafety and public-health impact. The position emphasizes domain expertise over AI experience and requires strong written and verbal communication.

Responsibilities include building a misuse taxonomy, designing safe evaluation scenarios, establishing risk severity, and advising on safety and governance. Independent contractor terms apply.