class AIMLDeveloper:
def __init__(self):
self.name = "Onur TΔ°LKΔ°"
self.role = "AI / ML Developer"
self.location = "Ankara, Turkey"
self.core_expertise = [
"End-to-end ML pipelines (data β model β deployment)",
"RAG-based systems and LLM integrations",
"Production-oriented development mindset"
]
def current_focus(self):
return "Designing practical AI systems with real-world constraints"
Binary classification for customer reorder prediction
LightGBM β’ Docker β’ Streamlit β’ Feature Engineering β’ Class Imbalance Handling
- F1 Score: 0.78 | Recall: 91% | Precision: 69% on 3M+ samples
- 15+ engineered features (user history, product popularity, temporal patterns)
- Complete ML pipeline: EDA β Baseline β Feature Engineering β Production
- Dockerized deployment on Hugging Face Spaces with interactive demo
Intelligent FAQ system for bootcamp participants
LangChain β’ ChromaDB β’ Sentence Transformers β’ MultiQueryRetriever β’ Streamlit
- Semantic search across 3,232 Q&A pairs with <3 second response time
- MultiQueryRetriever + MMR for improved retrieval accuracy (~95%)
- 40+ keyword mappings with hallucination prevention (<5% error rate)
- Deployed on Streamlit for 150+ concurrent users
Modular regression system with Kaggle validation
scikit-learn β’ Feature Engineering β’ RidgeCV β’ Automated Reporting
- End-to-end pipeline: data ingestion β feature engineering β training β evaluation
- Custom features (TotalSF, Age, BathCount) improving RMSE by 12%
- Automated JSON metrics + feature importance visualization
- Kaggle Score: 0.13049 RMSLE (0.94 RΒ² local validation)
|
|
|
| Certification | Project Outcome | Year |
|---|---|---|
| Akbank Generative AI Bootcamp | Built production RAG chatbot (3.2K Q&As, <3s latency) | 2025 |
| Google AI Essentials | Applied responsible AI principles in LLM systems | 2025 |
| Deep Learning with Keras (BTK) | Implemented CNN architectures for classification | 2025 |
Machine Learning Engineer β’ NLP Engineer β’ LLM Engineer
AI/ML Researcher β’ Generative AI Developer β’ MLOps Engineer
π§ Best way to reach me: mehmetonurt@gmail.com
β If you find my projects interesting, feel free to star them!