Ivan Zakazov is Founder and CEO of Compresr (YC W26), an AI-powered API that compresses LLM context by 100x without losing critical information. Compresr provides drop-in solutions for agents and RAG systems that cut token costs and improve accuracy.

Ivan completed his PhD at EPFL (Swiss Federal Institute of Technology Lausanne) researching LLM context compression and efficient ML systems. He previously worked at Microsoft and Philips Research, contributing to medical imaging and domain adaptation research.

Ivan has published multiple peer-reviewed papers at top conferences including MICCAI, with research focused on neural networks, domain adaptation, and efficient AI systems. His work bridges academic research and practical applications in natural language processing and computer vision.

Compresr was accepted into Y Combinator's Winter 2026 batch and is headquartered in San Francisco. The company offers an open-source compression proxy that works seamlessly with Claude Code and OpenClaw, enabling faster and cheaper AI agent workflows.

Compresr's technology enables 100x compression of LLM context, making AI applications faster, more cost-effective, and more accurate. The platform addresses critical bottlenecks in agentic workflows and has gained traction among developers building production AI systems.