Senior Research Scientist – AI Safety & Security

About the role

As a Senior Research Scientist in AI Safety and Security, you will join Google’s dedicated research team in Singapore focused on proactive threat mitigation, adversarial machine learning and trustworthy AI. You will work on the machine‑learning foundations that keep next‑generation AI models and intelligent agents robust against emerging risks.

Key responsibilities

• Drive foundational research in model robustness, continual learning, interpretability and multi‑objective optimisation.
• Design and implement rigorous evaluation protocols, scenario‑based benchmarks and stress‑testing methodologies for frontier AI systems.
• Curate advanced datasets and conduct fine‑tuning or optimisation experiments to enhance model resilience and enforce safety constraints.
• Collaborate with regional engineering hubs, product teams and academic partners to translate proofs‑of‑concept into production‑ready solutions.
• Publish groundbreaking research in top‑tier machine‑learning venues and engage with the broader academic and industry community.

Required profile

• PhD in Computer Science or a related field, or equivalent practical experience.
• At least 2 years leading a research agenda in machine learning, adversarial ML or AI safety.
• Track record of scientific publications in conferences such as NeurIPS, ICML, ICLR, CVPR or similar.

Required skills

• Python programming.
• Machine‑learning techniques including supervised, unsupervised and reinforcement learning.
• Adversarial machine learning, robustness, data poisoning, prompt injection and model backdoor detection.
• Interpretability, continual learning and generative‑model research.
• Multi‑objective optimisation and agentic AI security.

What we offer

• Competitive salary ranging from SGD 11,500 to SGD 23,000 per month.
• Opportunity to shape the future of trustworthy AI at a global technology leader.