Senior AI Safety & Security Research Scientist

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

Job summary

Google in Singapore seeks a Senior Research Scientist to lead AI safety and security research, focusing on robust ML foundations, continual learning, and interpretability. The role emphasizes proactive threat mitigation and evaluating frontier AI systems, with close collaboration across engineering and academia.

You will publish in top ML venues and contribute to next-generation trustworthy AI, working with regional teams to translate insights into production-ready solutions.

Qualifications

• PhD in Computer Science or related field, or equivalent practical experience.
• 2 years of experience leading a research agenda.
• Experience in ML, adversarial ML or evaluating frontier AI systems, incl. supervised/unsupervised/RL, interpretability, robustness, ML safety, generative models, agentic AI, multi-objective optimization.
• One or more publications in conferences, journals, or public repositories (CVPR/ICML/NeurIPS/ICLR, etc.).

Responsibilities

• Drive foundational ML research in model robustness, continual learning, interpretability, and multiobjective optimization to advance trustworthy AI.
• Design evaluation protocols, scenario-based benchmarks, and stress-testing to assess frontier AI capabilities and multi-agent consensus.
• Curate advanced datasets and conduct fine-tuning or optimization to enhance resilience and safety.
• Collaborate with regional engineering hubs, product teams, and academic partners to translate proofs-of-concept into production solutions.
• Publish groundbreaking research in machine learning venues and engage with academia and industry communities.

Skills

Research leadership

Machine learning

Adversarial ML

ML safety

Generative models

Reinforcement learning

ML interpretability

Python

Education

PhD in Computer Science or related field

Tools

Python

Job description

Google in Singapore seeks a Senior Research Scientist to lead AI safety and security research, focusing on robust ML foundations, continual learning, and interpretability. The role emphasizes proactive threat mitigation and evaluating frontier AI systems, with close collaboration across engineering and academia.

You will publish in top ML venues and contribute to next-generation trustworthy AI, working with regional teams to translate insights into production-ready solutions.