About the job
Come build and lead Gray Swan's biology safety capability from the ground up, serving as the technical authority on biological misuse risk across red-teaming, evaluation, benchmarking, defenses, and safety infrastructure development. You'll play a critical role in reducing biological risks from frontier AI systems through partnerships with leading AI labs, translating deep biological expertise into scalable AI safety systems that help define the industry's standards for evaluating dangerous capabilities.
Responsibilities
- Design and lead adversarial evaluations of frontier LLMs for biological misuse risks, including agent acquisition, pathogen characterisation and enhancement, biosecurity screening bypass, and emerging biotechnology capabilities across text, agentic, and multimodal systems.
- Partner closely with machine learning engineers and AI researchers to translate biological expertise into technical requirements for scalable evaluation datasets, classifiers, guardrails, benchmarks, fine-tuned models, and automated red-teaming for both internal products and frontier AI lab partners.
- Develop and maintain the B in Gray Swan's CBRN harm taxonomy, ensuring biological risk frameworks evolve alongside rapidly advancing model capabilities.
- Produce clear technical risk assessments and actionable recommendations for frontier AI labs, enterprise customers, policymakers, and internal stakeholders.
- Build, mentor, and lead a high-performing team of biology subject matter experts while establishing rigorous evaluation standards, quality processes, and scalable safety infrastructure.
- Represent Gray Swan as the company's biology safety expert through collaborations with AI labs, biosecurity organizations, government partners, and the broader AI safety research community.
Qualifications
Minimum
- PhD in biology, particularly in microbiology, virology, synthetic biology, protein engineering, or a closely related discipline, with postdoctoral or equivalent research experience.
- Deep understanding of biological misuse risks, dual-use research, pathogen biology, synthetic biology, or biosecurity.
- Experience conducting adversarial evaluations, biological risk assessments, AI safety research, or developing safety datasets for frontier AI systems.
- Familiarity with international biosecurity frameworks, dual-use governance, responsible biotechnology practices, and emerging AI safety standards.
- Comfortable operating at the intersection of cutting-edge biology, machine learning, and AI security.
- Thrive in ambiguous, fast-moving environments where you'll define strategy while building new systems from the ground up.
- A builder who enjoys creating teams, processes, and technical infrastructure, not simply maintaining existing programs.
Preferred
- Experience developing machine learning systems, biological safety classifiers, or evaluation pipelines for high-risk biological capabilities.
- Hands-on experience with frontier AI model evaluations, red-teaming, prompt engineering, or AI capability benchmarking.
- Experience working with government biosecurity organizations, frontier AI labs, or organizations focused on catastrophic biological risk.
- Publications or significant contributions in AI safety, biosecurity, synthetic biology, or dual-use governance.
- Strong programming or data science experience (Python, ML tooling, biological data analysis).