AI-Native Security Research Intern 2027

At IBM Research, we are the innovation engine of IBM, exploring what’s next in computing and shaping the technologies the world will rely on tomorrow. From advancing AI and hybrid cloud to pioneering practical quantum computing, we anticipate challenges and unlock new opportunities for clients, partners, and society. Working at IBM Research means joining a team that accelerates discovery at the intersection of high-performance computing, AI, quantum computing, and cloud technologies. You’ll collaborate with leading scientists, engineers, and visionaries to push boundaries and turn ideas into reality. With a culture built on curiosity, creativity, and collaboration, IBM Research offers the opportunity to grow your career while contributing to breakthroughs that transform industries and change the world. 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 Strong programming skills in languages such as Python, Rust, or Go Experience building, debugging, and testing software systems Knowledge of systems security and software security Excellent written and verbal communication skills Experience with AI agents and agentic software development Experience designing, conducting, and evaluating experiments Knowledge of access control and language-based security concepts Knowledge of distributed systems and operating system concepts