Research Scientist — AI Safety & Security

Google; Singapore; On-site; SGD 150,000 - 230,000; Full time

Job summary

Google is seeking a Research Scientist in Singapore to advance proactive threat mitigation, adversarial ML, and agentic security for next-generation AI systems. You will focus on ML foundations for AI safety, develop robust evaluation benchmarks, and collaborate with academic partners and regional engineers.

The role emphasizes continual learning, interpretability, and publishing cutting-edge research in top venues, contributing to trusted AI capabilities within Google’s global research efforts.

Qualifications

• PhD degree in Computer Science, a related field, or equivalent practical experience.
• Experience in machine learning, adversarial ML or evaluating frontier AI systems, including supervised/unsupervised/reinforcement learning, ML interpretability, adversarial robustness, ML safety, generative models, agentic AI, multi-objective optimization.
• One or more scientific publication submissions for conferences/journals/public repositories (CVPR, ICCV, NeurIPS, ICML, ICLR, etc.).

Responsibilities

• Drive foundational ML research in model robustness, continual learning, interpretability, and multiobjective optimization to advance trustworthy AI.
• Design and develop evaluation protocols, benchmarks, and stress-testing methodologies for frontier AI capabilities and multi-agent consensus.
• Curate advanced datasets and conduct fine-tuning or optimization experiments to enhance model resilience against emerging threats and ensure safety constraints.
• Collaborate with regional engineering hubs, core product teams, and academic partners to transition proofs-of-concept into robust production solutions.
• Publish groundbreaking research in ML venues and actively participate in academic/industry research communities.

Skills

Python

Machine learning

Publications

Education

PhD in CS or related field

Job description

Google is seeking a Research Scientist in Singapore to advance proactive threat mitigation, adversarial ML, and agentic security for next-generation AI systems. You will focus on ML foundations for AI safety, develop robust evaluation benchmarks, and collaborate with academic partners and regional engineers.

The role emphasizes continual learning, interpretability, and publishing cutting-edge research in top venues, contributing to trusted AI capabilities within Google’s global research efforts.