AI Biosecurity Researcher
Concordia AIVisit Concordia AI website
Beijing- and Singapore-based social enterprise conducting AI safety and governance research, advisory work, policy engagement, convenings, and frontier-model risk monitoring.
Beijing, China; Singapore
About Concordia AI
Concordia AI advances global AI safety and governance through research, consulting for AI companies and policymakers, convenings, policy work, and its Frontier AI Risk Monitoring Platform.
Skills
About the Role
You will conduct end-to-end research on frontier AI and biosecurity. You will build threat models and benchmarks, red-team high-risk biological tasks, test safeguards, and translate technical and policy developments into governance-focused research, recommendations, and proposals.
Requirements
- Master’s degree or above in Synthetic Biology, Computational Biology, Bioinformatics, Virology, Pathogen Biology, Biosecurity, or a related discipline
- AI
- Experimental design
- Data analysis
- Biosecurity threat modeling
- Benchmark development
- Risk assessment
- Chinese reading, writing, and spoken communication
Responsibilities
- Develop AI biosecurity threat models with domain experts
- Define risk thresholds and assessment criteria for large models, biology-specific models, AI agents, and automated labs
- Design and build benchmarks for AI biological capabilities and safety
- Assess model performance in biological knowledge, complex task execution, and safety risk identification
- Conduct red-teaming evaluations on high-risk biological tasks
- Identify safety vulnerabilities in models and agentic workflows
- Test and validate risk-mitigation strategies and safeguards
- Track AI biosecurity technical and policy developments
- Translate findings into research reports, policy recommendations, and technical proposals
Hiring Process
Written application form → online written test → 2 online interviews → 2-day in-person work trial