About

I'm Shan Rizvi, a context architect building AI systems that model human cognition through knowledge graphs, semantic memory, and psychological profiling. My work gives language models the ability to remember, reason, and respond with relationship awareness.

Recent projects include a 32-billion parameter scientific reasoning engine trained on landmark papers using knowledge graphs with supervised fine-tuning and reinforcement learning, a self-improving agentic knowledge graph for compound synthesis (second prize at AGI House's AI4Science Hackathon), the first queryable knowledge graph of 30 years of UN diplomatic history, an empathic AI companion with adaptive psychological profiling, and an open-source graph memory for LLMs.

I am driven by the conviction that harmonization of consciousness has been humanity's highest ambition across diverse cultures for thousands of years.

My electic pursuit of knowledge allows me to see bridges between neuroscience, mystical traditions, AI systems engineering, and geopolitical strategy. These aren't separate domains—they're different symbolic systems concerning the same underlying reality. What mystics intuited about consciousness, neuroscience now measures, and AI can operationalize.