About Me

Hello! My name is Eduard Hvizdak. I'm an AI engineer focused on building real-world systems powered by large language models. Most recently, I’ve been working on AI infrastructure for document intelligence, multi-agent pipelines, and retrieval-augmented knowledge systems.

My interests evolve with the problems I’m exploring, but lately I’ve been especially focused on agentic AI systems, retrieval architectures, and large-scale document analysis using modern embedding models and vector search.

My skillset spans a wide range of technologies, and I believe strongly in choosing the right tool for the problem rather than locking into a single framework or stack. I enjoy designing systems where language models interact with retrieval engines, structured data, and external tools to solve complex tasks. Much of my work involves building FastAPI backends, asynchronous pipelines, and vector search infrastructure that allows AI systems to operate reliably at scale.

Outside of programming, you’ll usually find me reading, experimenting with new technologies and occasionally scrolling Twitter.