GenAI Safety Research Scientist

A*STAR - Agency for Science, Technology and Research; Singapore; On-site; SGD 90,000 - 120,000; Full time

Job summary

The Trustworthy AI team at the Centre for Frontier AI Research (CFAR), IAIC, part of A*STAR, is seeking motivated scientists to research safety of generative AI and multi-agent systems. You will work with regulatory and clinical partners to develop evidence, testing tools and guidance for safe, real-world deployment of AI.

Responsibilities include red-teaming, risk-mitigation method development, and post-deployment monitoring to ensure robust, regulatory-grade outcomes for GenAI systems in

Qualifications

• PhD degree in Computer Science, Electrical & Electronic Engineering, Computer Engineering, Biomedical Engineering or a related field.
• Solid programming skills in Python and hands-on experience with deep learning frameworks such as PyTorch.
• Research experience in AI safety and security, adversarial machine learning, trustworthy machine learning, LLMs or VLMs, and multi-agent systems.
• Good communication and teamwork skills, and the ability to work with clinicians, regulators and engineers in a multidisciplinary setting.

Responsibilities

• Design and conduct systematic red-teaming and risk assessments of GenAI and multi-agent systems.
• Develop efficient guardrails and risk-mitigation methods, such as knowledge validation and anomaly detection.
• Develop methods for continuous post-deployment monitoring, including drift detection and real-time performance tracking.

Skills

Integrity

Critical Thinking

Innovativeness

Effective Communication

Education

PhD in Computer Science or related field

Tools

Python

PyTorch

Job description

The Trustworthy AI team at the Centre for Frontier AI Research (CFAR), IAIC, part of A*STAR, is seeking motivated scientists to research safety of generative AI and multi-agent systems. You will work with regulatory and clinical partners to develop evidence, testing tools and guidance for safe, real-world deployment of AI.

Responsibilities include red-teaming, risk-mitigation method development, and post-deployment monitoring to ensure robust, regulatory-grade outcomes for GenAI systems in