Research Scientist, AI Safety and Security

About the role

Google is seeking a Research Scientist to join its AI Safety and Security team in Singapore. The role focuses on proactive threat mitigation, adversarial machine learning, and securing next‑generation AI models and agents.

Key responsibilities

• Drive foundational research in model robustness, continual learning, interpretability, and multi‑objective optimization.
• Design rigorous evaluation protocols, scenario‑based benchmarks, and stress‑testing methodologies for frontier AI systems.
• Curate advanced datasets and conduct fine‑tuning experiments to enhance model resilience against emerging threats.
• Collaborate with regional engineering hubs, product teams, and academic partners to translate proofs‑of‑concept into production solutions.
• Publish groundbreaking research in top machine‑learning venues and represent Google at academic and industry events.

Required profile

• PhD in Computer Science or a related field, or equivalent practical experience.
• Strong publication record with submissions to conferences such as NeurIPS, ICML, ICLR, CVPR, or similar.
• Experience in machine learning, adversarial ML, or evaluating frontier AI systems.
• Demonstrated expertise in security‑focused AI research, including data poisoning, prompt injection, and model backdoor detection.

Required skills

• Proficiency in Python programming.