Aller au contenu
AI.info

jobs

Research Scientist, AI Safety and Security

As a Research Scientist, you will join a specialized research effort dedicated to proactive threat mitigation, adversarial machine learning, and agentic security.

En anglais

Company
Google
Location
Singapore
Status
Open
Posted
2026-11-18 16:39 UTC

A research scientist position on a Google team working on adversarial machine learning and agentic security. The work is foundational ML research: model robustness, continual learning, interpretability and multiobjective optimization, plus designing evaluation protocols, scenario benchmarks and stress tests for frontier models and multi-agent systems. The person also curates datasets and runs fine-tuning experiments, publishes at ML venues and works with academic partners. A PhD or equivalent experience is required, along with publications and a security-minded approach to model failure modes.

Original job posting