I’m interested in the complete lifecycle of intelligent applications—from developing machine learning models and building Generative AI applications to deploying, monitoring, and operating the infrastructure that keeps them running.
I work hands-on with technologies such as Python, Machine Learning, XGBoost, LangChain, SQL, Docker, Linux, APIs, cloud platforms, and self-hosted infrastructure. Rather than limiting my work to experiments and notebooks, I focus on turning ideas into working systems that can be deployed and used in real environments.
My projects include machine learning systems for business intelligence, AI applications connected to live databases, containerized services, and self-hosted infrastructure for running applications and AI workloads.
I’m continuously exploring how software, AI, and infrastructure come together to build systems that are not only intelligent, but also deployable, scalable, observable, and reliable.
Currently, I’m focused on building real-world projects, deepening my engineering skills, and turning ambitious ideas into production-ready systems.
01
Machine Learning
Classification and regression with Scikit-Learn and XGBoost, deep learning with TensorFlow and Keras, and model explainability with SHAP.
Scikit-Learn
XGBoost
TensorFlow
SHAP
02
AI & Generative AI
LLM applications with LangChain and LangGraph, RAG systems grounded in SQL and vector databases, and the OpenAI and Gemini APIs.
LangChain
LangGraph
RAG
OpenAI / Gemini
03
Cloud & Infrastructure
Containerized deployments with Docker on Linux servers, Coolify and Cloudflare Tunnel for self-hosting, and apps on Streamlit Cloud and Railway.
Docker
Linux
Coolify
Cloudflare