Kuyumcum
Product engineering · applied AI
A mobile ecosystem connecting precious-metal holdings, portfolio insight and local merchants. I co-developed the product and engineered its AI features.

Retrieval pipelines that ground language models in real documents, with evaluation that shows where every answer comes from.
Agents that call real tools through LangGraph and MCP: guarded loops, schemas on every write and a person in the loop where it matters.
Web apps from database to interface: Spring Boot services, typed React front ends and real-time updates.
Cross-platform Flutter apps on Firebase, with AI features built into everyday flows.
Models trained on messy public data, compared honestly and explained with the metrics that matter for the decision.
Software & AI engineer
AI instructor
Agentic AI & automation engineer
Agentic AI & automation engineer intern
Software engineering intern
Software engineering intern
Every ball is a tool from my own projects. Hover to name it, drag to move it.
Every tool here comes from my own projects; the list says where.

I’m Onur, an AI engineer based in İzmir, Türkiye. I build LLM applications end to end: retrieval, tool-calling agents with LangGraph and MCP, and the software around them.
Alongside my role at Future Is Now, I teach at ASTRO8 AI Academy: IT teams at large companies, from LLM fundamentals to agentic development with Claude Code and Codex.
I care about the decisions behind a system: how it handles uncertainty, how it is evaluated and how people use it.
Away from the keyboard, I’m on a basketball or tennis court.
Product engineering · applied AI
A mobile ecosystem connecting precious-metal holdings, portfolio insight and local merchants. I co-developed the product and engineered its AI features.
Machine learning · research
My two-layer machine-learning research on İzmir’s public water-quality data: current contamination detection and safety-trend forecasting, with real and synthetic evaluation kept distinct.


water-quality measurements from 76 sampling points, August 2025 – July 2026
Retrieval · LLM systems
I built a local RAG assistant for departmental knowledge with Llama 3.1, SBERT and FAISS: semantic retrieval, traceable context and deliberately constrained answers.
MCP · agent tooling
I built a personal strength coach end to end on Health Connect, Cloudflare and an OAuth-protected MCP server. Tested, deterministic analysis runs on the server; ChatGPT reads it through MCP and writes the coaching.
Shorter projects with their source code
My interests sit at the intersection of applied machine learning, data science and reliable AI systems. I want to understand how models behave beyond a single evaluation score.
Accepted · publication pending
International Journal of Engineering Approaches (IJEA)
A two-layer approach to current contamination detection and future water-safety trends.
Course project · not submitted for peer review
Three-person team, CE 477
25,775 daily İzmirim Kart ridership rows by operator and fare type, January 2021 – April 2025. DBSCAN clustering, seasonal features and demand forecasting with XGBoost and Random Forest.
Loading GitHub activity… See my profile on GitHub
Graduation certificate · the academy’s 2025–2026 AI training program.
Training completion certificate from the Google AI & Technology Academy.
Professional certificate · six courses covering traditional and agile project management.
Training completion certificate from the Google AI & Technology Academy.
Participation certificate from the Savunma Gelişim training program.
Participation certificate from the Savunma Gelişim training program.
Record of achievement · 80%. Model compression and low-bit quantization for efficient AI.
Participation certificate. CNNs, vision transformers, segmentation and detection with PyTorch.
Record of achievement · 78.3%. Software energy consumption and LLM performance measurement.
Good work starts with a conversation.
If you’d like to get in touch, feel free to write.



