About Matjaž

Matjaž has led multiple LLM integrations for US-based SaaS platforms, working on production systems that required high availability, predictable performance, and long-term maintainability. His experience includes designing scalable LLM-backed services, integrating them into existing architectures, and ensuring they could operate reliably under real user traffic. He is particularly comfortable working with complex systems where AI components must coexist with traditional software infrastructure.

He brings a strong engineering-first mindset to LLM development, treating AI features as core system components rather than experimental add-ons. Matjaž places a strong emphasis on clean architecture, observability, and operational stability, investing time in monitoring, fallback strategies, and clear interfaces between AI and non-AI services. His goal is to build LLM-powered systems that teams can confidently operate, extend, and scale over time without accumulating unnecessary technical debt.