AI Chemical Security Researcher

Concordia AI; Singapore; On-site; SGD 70,000 - 120,000; Full time

Job summary

Concordia AI in Singapore seeks a researcher to explore AI x chemistry with a focus on safety and governance. You will deliver risk assessments, benchmark AI chemical capabilities, and test mitigation strategies across policy, industry, and academia.

The role emphasizes cross-disciplinary collaboration, rigorous scientific reasoning, and the ability to drive frontier research independently while working with a proactive team.

Qualifications

• Master’s degree or above in a relevant chemistry field.
• Strong interest in AI x Chemical Security and responsible science.
• Solid domain expertise in chemistry for evaluating AI-generated outputs.

Responsibilities

• Conduct in-depth research at the intersection of frontier AI and chemistry.
• Develop risk and safety benchmarks for AI-enabled chemical tasks.
• Perform red-teaming evaluations and mitigation strategy studies.
• Track governance-relevant developments and translate findings into proposals.

Education

Master’s degree or above in Organic Chemistry, Medicinal Chemistry, Chemical Engineering, Toxicology, Chemical Biology, or a related field

Job description

Background

Concordia AI is committed to identifying and addressing the most pressing challenges arising from AI development, ensuring AI develops in a safe, reliable, and responsible way. The deep convergence of AI and chemistry is one of our primary focus areas. We recognize that while this convergence greatly accelerates drug discovery and chemical engineering, it also poses serious risks: lowering the barriers to synthesizing hazardous chemicals and chemical weapon precursors, raising the ceiling of potential harm, and undermining existing chemical defense and verification systems. Our published work and ongoing initiatives in this domain include:

• Engaging in CBRN Governance Dialogues: Continuously participating in UN technical and policy consultations regarding chemical, biological, radiological, and nuclear (CBRN) risks and dual-use threats posed by frontier AI.

Responsibilities

As a core team member at Concordia AI, you will conduct in-depth research at the intersection of frontier AI and chemistry, delivering key decision support for AI x chemical security governance across the policy, industry, and academic communities. Focusing on the capability boundaries and safety risks of general-purpose large models, chemistry-specific AI models, AI agents, and automated labs in synthesis planning, reaction condition optimization, and toxicity prediction, you will drive end-to-end research pipelines from risk identification to mitigation strategy development.

• AI x Chemical Security Threat Modeling: Collaborate with domain experts to develop chemical security threat models for general-purpose large models, chemistry-specific AI models, AI agents, and automated labs, defining risk thresholds and assessment criteria.
• AI x Chemical Security Benchmark Development: Independently design benchmarks for AI chemical capability and safety. Systematically assess model performance across chemical knowledge, task execution, and safety risk identification.
• AI x Chemical Red-Teaming & Mitigation Strategies: Conduct red-teaming evaluations on high-risk chemical tasks, and identify safety vulnerabilities across different models and systems. Explore and validate cutting-edge risk mitigation strategies and protective safeguards.
• Technical & Policy Tracking for Governance Support: Monitor developments in AI x Chemical Security across research and policy spheres, converting research findings into research reports, policy recommendations, and technical proposals that inform chemical security governance decisions.

Qualifications

Required

• Alignment with Concordia AI’s mission and a strong interest in AI x Chemical Security, combined with a strong sense of responsibility, problem-solving skills, and rigorous scientific reasoning skills. Ability to drive frontier research independently while remaining a collaborative, proactive team player.
• Master’s degree or above in Organic Chemistry, Medicinal Chemistry, Chemical Engineering, Toxicology, Chemical Biology, or a related field.
• Genuine interest in AI and a fast learner.
• Solid domain expertise in chemistry, capable of evaluating the technical feasibility and risk levels of AI-generated chemical outputs.
• Strong Chinese reading and writing skills, with proficient spoken Chinese for smooth communication.

Preferred

• Research or practical experience in chemical security evaluation, organic synthesis, toxicology, or hazardous chemical management.
• Hands-on experience in developing or applying AI models in chemistry/life sciences, or familiarity with cheminformatics tooling.
• Ability to communicate and collaborate effectively in both Chinese and English language with Chinese and international chemical security stakeholders.