Senior Staff Research Scientist, App and Ecosystem Trust

Google Google · Big Tech · Singapore

Research Scientist role focused on Android security and AI agent safety, developing novel research and agent-powered systems to detect and prevent various forms of abuse. The role involves analyzing codebases using ML and collaborating with internal and external partners.

What you'd actually do

  1. Identify threats and trends to help the team rapidly develop new strategies against evolving adversarial tactics and abuser bypass techniques.
  2. Develop and publish novel research on Android security and AI agent safety, collaborating with global academic and technical partners to improve defenses.
  3. Design neuro-symbolic and agent-powered systems to identify privacy threats, reverse-engineer apps, and ensure the safety of autonomous systems interacting with mobile web environments.
  4. Perform analysis on codebases (Java, JavaScript, Native) using machine learning to detect malware, bypass obfuscation, and neutralize evasion techniques.
  5. Work with teams across Google such as AdSpam, Android Platform, Actor Trust, and Google Research to address abuse problems collaboratively.

Skills

Required

  • PhD degree in Computer Science, a related field, or equivalent practical experience
  • 6 years of experience with research agendas across multiple teams or projects
  • One or more scientific publication submissions to conferences, journals, or public repositories (e.g., CVPR, ICCV, NeurIPS, ICML, ICLR)

Nice to have

  • 4 years of experience leading research efforts and influencing direction in machine learning, privacy, and security
  • 2 years of coding experience

What the JD emphasized

  • novel research
  • AI agent safety
  • agent-powered systems
  • machine learning
  • malware
  • adversarial tactics
  • abuser bypass techniques
  • privacy threats
  • reverse-engineer apps
  • autonomous systems
  • evasion techniques

Other signals

  • developing novel research
  • designing neuro-symbolic and agent-powered systems
  • performing analysis on codebases using machine learning