ByteDance
Research Scientist Intern (Security for AI) - 2026 Start (PhD)
San Jose, California · Internship · Posted Oct 28, 2026
- Education
- Currently pursuing a PhD in Computer Science or a related discipline.
About the job
Research LLM security solutions, assess vulnerabilities, and help strengthen secure AI practices across products.
What you'll do
- Design and develop defenses against LLM threats such as prompt injection and private information disclosure.
- Assess security risks and recommend mitigations; monitor AI risks and emerging technologies.
- Collaborate on and improve AI security practices, including guidance and training.
What they ask for
- Currently pursuing a PhD in Computer Science or a related discipline.
- Excellent knowledge of LLM and foundation-model theory and practice.
- Strong publication record at conferences such as NeurIPS, ICML, ICLR, ACL, or EMNLP.
Nice to have
- Communication and collaboration skills, plus demonstrated software engineering, NLP, or deep learning experience.
- Strong coding ability; familiarity with data structures and algorithms; proficiency in Python, Go, or Java.
Tools
Large Language Models (LLMs), foundation model, Python, Go, Java
AI focus
AI security research focused on LLM robustness, prompt injection, private information disclosure, and vulnerability mitigation.
Model-written summary · the original posting is authoritative