jobs
Senior Research Scientist, AI Safety and Security
In this role, you will join a specialized research effort dedicated to proactive threat mitigation, adversarial machine learning, and agentic security. Our team operates at trustworthy AI, focusing…
- Company
- Location
- Singapore
- Status
- Closed
- Posted
- 2026-10-16 11:39 UTC
A senior research position on a Google team in Singapore working on AI safety and security, specifically adversarial machine learning, agentic security and threats to frontier models. The work covers the machine-learning side of safety: model robustness, continual learning, interpretability, multiobjective optimization, plus building evaluation protocols, scenario-based benchmarks and stress tests for frontier and multi-agent systems, and curating datasets with fine-tuning experiments. Applicants need a PhD or equivalent experience, two years leading a research agenda, and a publication record. Preferred: Python, red-teaming, prompt injection and backdoor detection experience.
Original job posting