Staff Research Scientist, AI Alignment

About the role

Google is seeking a Staff Research Scientist to lead AI alignment efforts in its Singapore hub. You will bridge cutting‑edge academic breakthroughs with large‑scale engineering, ensuring that next‑generation AI models are robust, trustworthy, and safe.

Key responsibilities

• Design and execute large‑scale experiments to evaluate frontier AI systems.
• Develop and prototype novel AI safety techniques, including adversarial robustness and interpretability.
• Publish research findings in top conferences and journals.
• Build and coordinate research partnerships with universities, government bodies, and industry stakeholders across the APAC region.
• Translate research outcomes into scalable engineering solutions for Google products.

Required profile

• PhD in Computer Science or a related field, or equivalent practical experience.
• At least 4 years of research experience across multiple teams or projects.
• Track record of scientific publications in venues such as NeurIPS, ICML, ICLR, CVPR, etc.
• Experience working on machine learning, adversarial ML, or AI safety topics.

Required skills

• Machine learning
• Adversarial machine learning
• Supervised learning
• Unsupervised learning
• Reinforcement learning
• ML interpretability
• Adversarial robustness
• ML safety
• Generative models
• Agentic AI
• Multi‑object optimization

What we offer

• Opportunity to influence the safety of globally deployed AI systems.
• Collaboration with world‑leading researchers and engineers.
• Access to Google’s extensive computational resources and research infrastructure.