Senior Frontier AI Safety Research Scientist

Google; Singapore; On-site; SGD 180,000 - 240,000; Full time

Job summary

Google Singapore is seeking a researcher to join a specialized team focused on proactive threat mitigation, adversarial machine learning, and agentic security. The role targets developing ML foundations for AI safety, interpretability, and robustness while collaborating with academic partners and global engineering teams.

You will contribute to evaluating frontier AI systems, publishing results, and building benchmarks that inform next-generation trustworthy AI capabilities.

Qualifications

• PhD in Computer Science or related field or equivalent practical experience.
• 2 years of experience leading a research agenda.
• Experience in machine learning, adversarial ML or evaluating frontier AI systems.
• One or more scientific publication submissions to conferences/journals.

Responsibilities

• Drive foundational ML research in model robustness and interpretability.
• Design evaluation protocols and benchmarks for frontier AI.
• Curate datasets and run fine-tuning/optimization to improve robustness.
• Collaborate with regional hubs, product teams and academics to deploy ideas.
• Publish research in ML and AI venues and engage with communities.

Skills

ML research

Adversarial ML

ML safety

Research leadership

Publications

AI safety

Education

PhD in Computer Science or related field

Tools

Python

Job description

Google Singapore is seeking a researcher to join a specialized team focused on proactive threat mitigation, adversarial machine learning, and agentic security. The role targets developing ML foundations for AI safety, interpretability, and robustness while collaborating with academic partners and global engineering teams.

You will contribute to evaluating frontier AI systems, publishing results, and building benchmarks that inform next-generation trustworthy AI capabilities.