Bio
Preeti is an applied research leader who has delivered security outcomes by ensuring AI systems are reliable, safe and secure for over a decade across Fortune 500 and scaleups. As a recognized industry voice, Preeti holds multiple patents and publications in AI security, and speaks at popular industry and academic venues like Defcon, [un]prompted, ICML. She is currently focused on building and deploying effective AI control systems which account for human factors complementing technical measures.
What we’re looking for in a Mentee
- Excellent communicator
- Agentic, with a Getting-Stuff-Done attitude
- Experience with empirical research
What we’re like as Mentors
Jess & Preeti: As a mentor, I’ll mainly provide high-level guidance but am also happy to jump in on hands-on engineering questions & pair programming to get things unblocked.
Past fellows valued clear and strategic guidance on project scoping and research direction, and detailed feedback on experiment design and technical setups.
We’ll have weekly group sessions but will also be available for 1:1s to talk through anything you might want feedback on
Testimonials from past mentees - https://www.linkedin.com/in/preeti-ravindra/details/recommendations/
Past projects from mentors - https://sparai.org/projects/f26/recyQRpX2HbOZfHYp/, https://arxiv.org/pdf/2607.14570, https://prism-research.org/projects