GenAI Safety Scientist — Reg-grade AI Risk & Tools

A*STAR RESEARCH ENTITIES; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

The Trustworthy AI team at CFAR, IAIC under A*STAR RESEARCH ENTITIES is seeking scientists to study the safety of GenAI and multi‑agent systems. You will design red‑teaming, develop guardrails, and translate findings into regulatory‑grade toolkits with real‑world impact.

Applicants should have a PhD and strong Python/PyTorch experience, with ability to collaborate with clinicians, regulators and engineers to advance AI safety in healthcare settings.

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 PyTorch.
• Research experience in AI safety and security, adversarial ML, trustworthy ML or multi-agent systems.

Responsibilities

• Design and conduct red‑teaming and risk assessments of GenAI and multi‑agent systems.
• Develop guardrails, risk‑mitigation methods and automated flagging for high‑risk outputs.
• Develop methods for continuous post‑deployment monitoring and anomaly alerting.

Skills

Interdisciplinary collaboration

Communication

Critical thinking

Education

PhD in Computer Science / ECE / Biomedical Engineering

Tools

Python

PyTorch

Job description

The Trustworthy AI team at CFAR, IAIC under A*STAR RESEARCH ENTITIES is seeking scientists to study the safety of GenAI and multi‑agent systems. You will design red‑teaming, develop guardrails, and translate findings into regulatory‑grade toolkits with real‑world impact.

Applicants should have a PhD and strong Python/PyTorch experience, with ability to collaborate with clinicians, regulators and engineers to advance AI safety in healthcare settings.