About the role#
This PhD internship focuses on the security of Large Language Models and their applications. You will join the Security AI team to design and build frameworks that protect AI systems. The role provides an opportunity to contribute to research and product development while working with industry experts.
What you'll need#
- Currently pursuing a PhD in Computer Science or a related field.
- Knowledge of LLM and foundation model theory and practice.
- A strong publication record at conferences such as NeurIPS, ICML, ICLR, ACL, or EMNLP.
- Proficiency in Python, Go, or Java is preferred.
- Experience in software engineering, natural language processing, or deep learning through internships, work, or coding competitions is preferred.
- Strong coding ability with a focus on data structures and algorithms.
- Competition achievements in events like ACM/ICPC, USACO/NOI/IOI, Top Coder, or Kaggle are a plus.
- Strong communication and collaboration skills are preferred.
What you'll do#
- Design and develop security solutions for LLMs to improve robustness against prompt injections and private information disclosure.
- Perform security risk assessments and recommend mitigations for LLM vulnerabilities.
- Monitor existing AI risks and identify new opportunities to strengthen product security.
- Collaborate with external organizations and experts to track advancements in AI security.
- Evaluate and optimize internal AI security processes.
- Provide guidance to clients on adopting secure AI practices.
- Create and deliver training programs on secure AI principles.
Location & details#
- Location: San Jose, California, United States.
- Modality: On-site.
- Employment: Full-time internship.
- Term: Rolling basis.
- Compensation: $60 per hour.


