SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 150,000 - 178,000 / annual
Spectrum Labs is seeking a GenAI Biosecurity Expert to evaluate and strengthen safety guardrails for generative AI systems. This role combines deep biological science expertise with hands-on AI safety work to identify dual-use risks and prevent biological threat proliferation.
You will conduct adversarial red-teaming and risk evaluations to stress-test AI models against biological vulnerabilities. Your domain expertise and understanding of regulatory standards will translate into actionable feedback for model safety alignment. You'll stay current on emerging biotechnology research, biological threat vectors, and biosecurity governance to continually update safety benchmarks.
Key responsibilities include:
- Hands-on adversarial red-teaming and risk evaluations of AI models
- Translating biological domain expertise into AI safety feedback
- Monitoring emerging biotech research and threat vectors
- Updating safety benchmarks based on regulatory and scientific developments
- Prompt engineering and LLM output evaluation
Required qualifications:
- Ph.D. in Molecular Biology, Genetics, Microbiology, Virology, Biotechnology, Bioengineering, or related field (Master's with 5+ years relevant experience considered)
- Demonstrated hands-on or research experience in biological risk assessment, biosafety, or biosecurity governance
- Strong enthusiasm for prompt engineering, red-teaming, and LLM evaluation
- Excellent scientific rigor and analytical skills
- Ability to communicate complex scientific risks to technical AI safety teams
Preferred qualifications include knowledge of AI prompt engineering, familiarity with frontier AI safety benchmarks and evaluation frameworks, and expertise in pathogen analysis, dual-use biotech/genetic modification, or toxin research and biomanufacturing.
