Current Focus

From Engineering Realityto AI-Enabled Systems

These are not fixed boundaries, but the technical directions in which I am currently deepening my profile.

07.1Empowering LLMs to Act

AI Agents · MCP · RAG Workflows

I focus on AI Agents, MCP, and RAG workflows because AI is moving from isolated text generation toward systems capable of action. Agents structure tasks, call tools, and execute multi-step workflows. MCP connects models, tools, and data sources through standardized interfaces, while RAG brings in current, domain-specific knowledge. For me, this is the next step of productive AI — systems that meaningfully connect knowledge, context, and action.

07.2AI Meets the Physical World

Industrial Digitalization · IoT

Industrial digitalization interests me most where data does not stop at dashboards, but flows back into real processes. Sensors, edge and IoT systems, process data, and machine states form the bridge between physical reality and digital decision-making. This is where AI becomes practical: not as an isolated model, but as part of a system that supports machines, processes, and people.

07.3Data Flows as Technical Infrastructure

Data Engineering · System Thinking

Data analysis does not begin with the model. It begins where data is created, cleaned, structured, connected, and made reliably available. That is why I see data engineering as the technical foundation for everything that follows: analytics, machine learning, reporting, automation, and decision support. Good data architecture is not a backend detail to me — it is part of the system’s actual performance.

07.4From Idea to Operable System

DevOps · Cloud Deployment · Serverless

I am interested not only in whether a solution works, but also in whether it can be deployed, operated, and improved reliably. Cloud deployment, DevOps practices, and serverless architectures help turn prototypes into robust systems. For me, this is the transition from technical idea to productive reality: reproducible, maintainable, scalable, and understandable.

Direction

Thinking of Engineering, Data, AI, and Cloud as One System

My current direction is to treat engineering, data, AI, and cloud infrastructure not as separate technical modules, but as one connected system. I am less interested in isolated buzzwords than in how these layers work together under real-world conditions — in industrial systems, scientific applications, and digital products.