Similar Jobs

See all

Responsibilities:

  • Review cybersecurity prompts submitted to an AI system that could not be confidently classified as benign or malicious.
  • Determine the underlying intent and goal behind each prompt, and assess whether the user is pursuing a legitimate purpose or an intent to cause harm.
  • Apply deep domain expertise to judge technical context, specificity, and real-world uplift a response would give an attacker.

Requirements:

  • Minimum of 5 years of proven, hands-on experience in Windows malware analysis and research.
  • Strong command of Windows internals and the Win32/NT API, including process injection, persistence, privilege escalation, and EDR/AV evasion techniques.
  • Experience with static and dynamic analysis of PE files, including unpacking, deobfuscation, and use of x64dbg, IDA, Ghidra.

About the company:

  • Builds specialized evaluation infrastructure for AI safety and robustness testing.
  • Platform simulates adversarial conditions used by AI development teams to validate agent behavior before deployment.
  • Currently expanding a freelance contributor pool for scenario and environment development.

SafetyTech Client #1

They build specialized evaluation infrastructure for AI safety and robustness testing. Their platform simulates adversarial conditions used by AI development teams to validate agent behavior before deployment.

Apply for This Position