AI-Native Security Research Intern 2027

We are looking to grow our team of research scientists and engineers. AI agents are being integrated across the technology stack and granted access to extensive computational and data resources. While these capabilities have immense potential to increase productivity and accelerate scientific discovery, they also introduce significant security risks.

We are looking for candidates who can help us address the real-world security challenges posed by AI agents and develop systems that provide strong security guarantees. Successful candidates will design, implement, and evaluate state-of-the-art tools and systems to secure AI agents and agentic applications. The ideal candidate will have experience with AI agents, vulnerability discovery and analysis, and system hardening.

Your primary responsibilities will include:

• Designing systems to address emerging security risks
• Creating proof of concept implementations
• Conducting experiments, evaluations, and data analysis
• Communicating technical ideas and research findings to others