Join Us
The Secure Reasoning Lab is recruiting self-motivated Ph.D. students and postdocs to work on large language models and cybersecurity.
Who we look for
You do not need to have done all of the following, but a strong fit usually includes some of:
- Interest in LLMs, agents, or reinforcement learning, especially for security or software engineering
- Experience with systems security, program analysis, fuzzing, or program repair
- Solid programming and experimental skills
- Curiosity about both attacking and defending AI systems
How to apply
Email Prof. Jiahao Yu at jy5951@nyu.edu with:
- A short note on why you want to join SRL and what you want to work on
- CV
- Transcript (students)
- Representative papers or project links, if you have them
Please put [SRL Application] in the subject line.
Ph.D. applicants should also follow the NYUAD graduate admissions process for Computer Engineering / relevant programs.
PI
More background is on Jiahao Yu’s personal page and in his CV.