Pavan Reddy

Pavan is an AI engineer specializing in securing AI models and pipelines, with expertise in threat modeling, red-teaming, and hardening LLM and RAG systems against prompt injection, data leakage, and supply-chain risks. His research explores emerging attack vectors and practical defenses, with publications at AAAI FSS on EchoLeak and on safer deployment of AI chatbots in healthcare. He builds assurance into the ML lifecycle, from dataset integrity and model governance to runtime monitoring and incident response, bridging policy, risk, and engineering. He also teaches AI and ML online to an audience of over 90k on Instagram.