About the role
TL;DR
Evaluate AI systems for biological safety and misuse risks.
- •About 10a Labs: 10a Labs is the safety and threat-intelligence layer trusted by frontier AI labs, AI unicorns, Fortune 10 companies, and leading global technology platforms.
- •Our adversarial red teaming, model evaluations, and intelligence collection enable engineering, safety, and security teams to stay ahead of evolving threats and deploy AI systems safely.
- •Location & Travel Expectations We are primarily seeking candidates based in the Washington, DC, New York City, San Francisco Bay Area, and Denver metropolitan areas.
- •Candidates hired in these locations will be expected to work from a 10a Labs office at least two days per week.
- •All new hires will participate in in-person onboarding in Washington, DC, New York City, or San Francisco during their first week.
- •Occasional travel may also be required for interviews, in-person meetings, and other business needs.
- •Position Overview We are seeking a Virologist with expertise in virology, microbiology, and biosecurity to support the design and execution of technical evaluations of advanced artificial intelligence (AI) systems, including Large Language Models (LLMs).
- •The ideal candidate will have a strong scientific background in biological research, an understanding of dual-use biological risks, and an interest in evaluating the capabilities and potential misuse risks of emerging AI technologies.
- •This role will focus on developing scientifically rigorous benchmarks, designing and conducting model evaluations, and assessing AI-generated scientific outputs for technical accuracy, feasibility, and potential implications for biological safety and security.
- •The candidate will work closely with multidisciplinary teams of scientists, AI researchers, and engineers to develop evaluation methodologies and communicate findings to stakeholders.
- •Key Responsibilities Design and develop scientific benchmarks and evaluation methodologies to assess the biological knowledge, reasoning, and technical capabilities of advanced AI models.
- •Conduct model capability evaluations and red-teaming exercises to assess potential biological misuse risks associated with advanced AI systems.
- •Develop scientifically grounded evaluation scenarios, questions, and tasks spanning virology, microbiology, and other relevant biological domains.
- •Assess AI-generated scientific outputs for technical accuracy, feasibility, completeness, and potential implications for biosecurity.
- •Identify and characterize potential misuse scenarios involving biological agents, dual-use research, and emerging AI capabilities.
- •Contribute to the development of evaluation criteria, scoring rubrics, and methodologies for measuring model performance and potential capability uplift.
- •Collaborate with AI researchers, engineers, and subject matter experts to develop and implement scalable evaluation approaches, including automated benchmarks.
- •Analyze evaluation results, identify patterns in model capabilities and limitations, and contribute to technical reports and client deliverables.
- •Stay informed of emerging developments in biological research, AI capabilities, biosecurity risks, and relevant AI safety frameworks to inform evaluation design.
- •Minimum Qualifications PhD in Virology, Microbiology, Molecular Biology, or a closely related biological science, or equivalent practical experience.
- •Research experience involving pathogenic viruses, bacteria, or other biologically relevant systems.
- •Strong understanding of biological research methods, experimental design, and the technical challenges associated with biological research and development.
- •Demonstrated knowledge of biosecurity principles, dual-use biological research, and potential biological misuse risks.
- •Experience critically evaluating scientific literature, experimental methodologies, and technical research outputs.
- •Strong analytical skills and the ability to assess complex scientific information for accuracy, feasibility, and technical limitations.
- •Experience preparing technical reports, presenting scientific findings, and communicating complex concepts to multidisciplinary audiences.
- •Preferred Qualifications Experience conducting AI model evaluations, developing scientific benchmarks, or assessing the capabilities and limitations of LLMs.
- •Experience with AI red-teaming, biological risk assessments, or evaluating potential misuse scenarios involving emerging technologies.
- •Hands-on experience in virology or microbiology laboratories, including work in BSL-2 or higher containment environments.
- •Experience using command-line tools, programming languages (e.g., Python), or computational approaches relevant to biological research.
- •Familiarity with AI-assisted biological research tools, including applications in experimental design, bioinformatics, or scientific reasoning.
- •Understanding of biological weapons threats, dual-use research concerns, and potential biosecurity risk mitigation approaches.
- •Familiarity with AI safety and capability assessment frameworks, including approaches used to evaluate biological and chemical risks associated with advanced AI systems.
- •Awareness of relevant biosecurity policies, international agreements, and stakeholders, including the Biological Weapons Convention.
- •Experience developing evaluation datasets, scoring rubrics, or structured methodologies for assessing scientific performance.
- •Demonstrated experience applying AI tools to biological research workflows, scientific analysis, or benchmark development.
- •Interest in emerging AI capabilities and their implications for scientific research, biological security, and AI safety.
- •Ideal Candidate The ideal candidate combines deep biological expertise with strong scientific reasoning and an interest in understanding the capabilities and limitations of advanced AI systems.
- •They are comfortable designing challenging scientific evaluation tasks, critically assessing technical outputs, and translating complex biological concepts into structured, measurable evaluation criteria.
- •They are particularly interested in developing rigorous and reproducible approaches to assessing AI capabilities and potential risks, and enjoy collaborating across scientific and technical disciplines.
- •Contract Details Duration: Per Needed Basis Commitment: Dependent on work load Location: Remote
- •United States Employment Type: Contract
Required skills
PythonOpenAI APIAnthropic APIGemini APILangChainHugging FaceGit
Nice-to-have skills
Penetration Testing
Domain expertise
biotechdeeptech
Tech stack
PythonOpenAI APIAnthropic APIGemini APILangChainHugging FaceGit