Research Intern, AI Security - FRA

At Fujitsu, we are driven by our purpose to make the world more sustainable by building trust in society through innovation. We have been a pioneer in technology and innovation for over 80 years, and we are committed to using our expertise to help businesses and organizations transform for the digital age. We believe that digital transformation is essential to creating a more sustainable future and are working with our customers to develop solutions that reduce environmental impact, improve efficiency, and create a more equitable society. We are committed to contributing to the United Nations Sustainable Development Goals (SDGs) and believe technology can play a vital role in achieving them.

The Security Science Laboratory (SS Lab) at Fujitsu specializes in integrating research in AI and security to build trust in the increasingly diverse digital society. We are seeking exceptional interns to join our SS Lab in the U.S. for fall through spring. This position provides an opportunity to solve problems on safety, privacy, and AI alignment in LLM-based agentic systems and robotics. We value individuals with vision to pick up new knowledge, see through complex scenarios, and arrive at simple, elegant yet workable solutions. Self-driven nature, creativity, communication skills, and attention to detail are traits of a successful researcher in this role. An intern has the option to work either full-time or part-time during the academic year.

Responsibilities

• Develop algorithms and systems, conduct experiments, and analyze the results.
• Potential research topics include, but are not limited to:
  • Detecting and preventing multi-turn and multi-stage jailbreaking
  • Adversarial coordination
  • Data poisoning
  • Contextual privacy leakage
  • Improving misalignment with user perceptions in agentic AI systems and robotics
• Publish research papers in scientific conferences on AI, NLP, ML, and security.
• Showcase the work via presentations in talks, conferences, and workshops.

Requirements

• Currently enrolled in a PhD program in computer science or a related discipline, with demonstrated research experience applying AI, NLP, and/or ML techniques to security and privacy challenges in agentic AI or robotics.
• Track record of coming up with new ideas or improving upon existing ideas in computing, demonstrated by accomplishments such as publications, projects, or competitions.
• Experience in evaluating tools and technologies in processing data from diverse but specialized fields of science.

Location: Pittsburgh, Pennsylvania (multiple locations in the country available). Relocation support is not provided. Visa sponsorship is not available.