Pioneering AI Safety & Security Research Scientist

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

Job summary

Google LLC is recruiting a Research Scientist for AI Safety and Security in Singapore. The role focuses on proactive threat mitigation, adversarial ML, and secure, trustworthy AI models.

You will contribute to our foundational ML research, develop evaluation benchmarks, and collaborate with engineers and researchers across regions. You will advance ML safety through robustness, continual learning, and interpretability while publishing in top venues and shaping next-generation AI security

Qualifications

• PhD in Computer Science, a related field, or equivalent practical experience.
• Experience in machine learning, adversarial machine learning or evaluating frontier AI systems, including supervised/unsupervised/ RL, ML interpretability, adversarial robustness, ML safety, generative models, agentic AI, and multi-objective optimization.
• One or more scientific publications submitted to conferences, journals, or public repositories (e.g., CVPR, ICCV, NeurIPS, ICML, ICLR).

Responsibilities

• Drive foundational ML research in model robustness, continual learning, interpretability, and multi-objective optimization for trustworthy AI.
• Design and develop evaluation protocols, scenario benchmarks, and stress-testing methodologies for frontier AI capabilities and multi-agent systems.
• Curate datasets and conduct fine-tuning/optimization to enhance model resilience and safety compliance.
• Collaborate with regional engineering hubs, core product teams, and academic partners to translate proofs-of-concept into production-ready solutions.
• Publish groundbreaking research in ML venues and contribute to academic/industry communities.

Skills

ML research

Adversarial ML

Evaluation of frontier AI

Scientific communication

Education

PhD in Computer Science or related field

Tools

Python

Job description

Google LLC is recruiting a Research Scientist for AI Safety and Security in Singapore. The role focuses on proactive threat mitigation, adversarial ML, and secure, trustworthy AI models.

You will contribute to our foundational ML research, develop evaluation benchmarks, and collaborate with engineers and researchers across regions. You will advance ML safety through robustness, continual learning, and interpretability while publishing in top venues and shaping next-generation AI security