Bio
Swaleha Parvin is an AI researcher and developer specializing in AI security, safety, and productivity systems. She is the creator of SafeGuardLLM, an enterprise-grade platform for systematic LLM vulnerability assessments, integrating real-world attack simulations across multiple AI providers.
Her expertise spans multi-agent AI workflows, Retrieval-Augmented Generation (RAG) architectures, and LLM orchestration, with a focus on prompt injection prevention, policy compliance, and automated AI red-teaming.
She has spoken at Google Gurgaon and CodersHQ Dubai, and regularly collaborates with AI engineers, researchers, and startups to build ethical, resilient AI solutions.