🛠 Tech Stack

💼 About This Role

You'll investigate how adversaries exploit generative AI systems like LLMs and on-device assistants, translating your findings into defensive capabilities within Origin's endpoint security products for the AI era. Your hands-on research will shape public-facing content and impact product direction.

🎯 What You'll Do

• Conduct research into adversarial tradecraft exploiting generative AI tools
• Research adversarial prompting, jailbreaks, and AI-enabled attack vectors
• Translate research findings into actionable product improvements
• Produce public-facing security research content

📋 Requirements

• 2+ years in red team operations or purple teaming
• 2+ years in defensive security research for publication or feature development
• Ability to write code for research tooling development

✨ Nice to Have

• Experience investigating or exploiting generative AI systems
• Contributions to open-source AI or security tooling
• Proficiency in a systems language like Rust or C/C++

🎁 Benefits & Perks

• 🏥 Generous healthcare coverage
• 🏖️ Flexible PTO
• 🏡 Home-office support