Iason Malkotsis

I am Iason Malkotsis, an engineer focusing on agentic AI, LLM evaluation, reliability & guardrails. I orchestrate multi-step planning, tool-calling, structured outputs, and robust monitoring to create auditable, reliable AI systems. I have built production-grade, human-in-the-loop agents and evaluation harnesses, translating research into deployed tooling for EU-funded projects. I hold an MSc in Networks & Systems Security and am strongest in Python, with strong background in systems design, security, and on-device/edge computing; I am comfortable with Docker, Kubernetes, CI/CD, and building scalable evaluation pipelines.

In Montreal-based practice, I blend academic rigor with hands-on software engineering to ship robust AI tooling. I enjoy collaboration, experimentation, and continuous learning as I translate complex AI research into practical, reliable software solutions.