Aman Priyanshu

AI Researcher (Security Foundation Models - Reasoning & Instruct)

Hi, I'm Aman!

I'm an AI Researcher at Foundation-AI (Cisco, part of Robust Intelligence startup acquisition) specializing in foundation models for security applications, particularly reasoning, long-horizon planning, and agentic systems. I've trained 8B-20B parameter models across multi-node GPU clusters (50+ GPUs). My research spans AI for security, AI security, privacy-preserving ML, and LLM safety, with work deployed in production models that have seen 300K+ downloads (in 2025 alone). My AI Safety work has been featured in SC Magazine, The Register, and other outlets, and led to invitations to OpenAI's Red Teaming Network and Anthropic's Model Safety Bug Bounty Program.

With a Masters in Privacy Engineering from Carnegie Mellon University, I've published at venues like USENIX and AAAI. I worked with Professor Norman Sadeh on LLM security research and Niloofar Mireshghallah on privacy-preserving ML. Currently, I build specialized RL environments for security domains, including custom CTF environments for automated penetration testing curriculum training and vulnerability detection frameworks for iterative code patch discovery.