Staff Research Scientist, AI Alignment

About the role

Google is seeking a Staff Research Scientist to lead AI alignment research in its Singapore hub. The role focuses on designing and executing large‑scale experiments that evaluate and improve the safety, robustness, and trustworthiness of frontier AI systems.

Key responsibilities

• Set up and run large‑scale tests of advanced AI models, covering supervised, unsupervised, and reinforcement learning paradigms.
• Develop and prototype novel algorithms for interpretability, adversarial robustness, and multi‑objective optimization.
• Publish research findings in top conferences and collaborate with external academic partners and government bodies across the APAC region.
• Translate breakthrough research into scalable engineering solutions that can be integrated into Google products.
• Act as a liaison for AI safety initiatives, shaping policy and regulatory compliance strategies.

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 leading ML or AI conferences (e.g., NeurIPS, ICML, ICLR).
• Experience working on AI safety, adversarial machine learning, or evaluating frontier AI systems.
• Ability to build and manage research partnerships with academic institutions and government agencies, especially within the APAC landscape.

Required skills

• Machine learning, including supervised, unsupervised and reinforcement learning.
• Adversarial machine learning and robustness techniques.
• ML interpretability and safety methods.
• Generative models and agentic AI concepts.
• Multi‑object optimization.