Computer Vision
- YOLO / YOLOE
- U-Net
- GAN / DCGAN
- OpenCV
- BoT-SORT
- ByteTrack
- Real-time video analytics
About
From research notebooks to production.
My work focuses on computer vision, multi-object tracking, segmentation, legal AI / RAG systems, remote-sensing workflows, and backend infrastructure for ML products.
I enjoy designing end-to-end pipelines: from data ingestion, model experimentation, retrieval systems, and evaluation to FastAPI services, Docker/Kubernetes deployments, observability, and production iteration.
I like building systems that are not only accurate, but also observable, maintainable, deployable, and usable.
What I like building
- Production-ready AI APIs
- Retrieval-augmented generation systems
- Computer vision pipelines for real-world camera setups
- Geospatial AI tools
- ML systems with clean architecture
- Developer-friendly AI products
- Research prototypes that can actually become usable software
Current focus
Where I spend my time
RAG & NLP
- Hybrid retrieval
- Dense + sparse search
- Reranking
- Qdrant
- pgvector
- Hugging Face
- Citation-aware LLM systems
Production Systems
- FastAPI
- PostgreSQL
- Redis
- Celery
- Docker
- Kubernetes / K3s
- Linux
- REST APIs
MLOps & Observability
- OpenTelemetry
- Prometheus
- Grafana
- Structured logging
- Deployment pipelines
EO / GIS
- Google Earth Engine
- Sentinel / Landsat imagery
- Urban heat island analysis
- Geospatial segmentation
Selected work
Systems I have built
01
Legal AI & RAG Systems
Built production-oriented Turkish legal AI workflows that deliver cited, real-time answers over legislation and case law.
- Dual-pipeline RAG for procedural law and case-law retrieval
- Hybrid retrieval with dense vectors and keyword search
- Cross-encoder reranking
- Numeric citation handling
- SSE-based LLM streaming
- FastAPI with PostgreSQL, pgvector, Redis, Celery, JWT/API keys, RBAC, rate limits and audit logs
- Kubernetes/K3s deployment with TLS, monitoring and observability
02
Real-Time Marina Vessel Tracking
Designed and deployed a real-time vessel tracking system from overhead CCTV footage.
- Boat detection with YOLO-based models
- Travel-lift / boat-hoist detection with YOLOE segmentation
- Multi-object tracking with BoT-SORT
- Zone and line-crossing logic
- Debounce state machines for reliable counting
- Annotated output videos with live HUD and entry/exit counters
03
EO / GIS & Remote Sensing
Worked on Earth Observation and geospatial AI workflows for climate and urban analysis.
- U-Net segmentation workflows
- Sentinel/Landsat imagery processing
- Urban heat island analysis
- Google Earth Engine pipelines
- Reproducible training and evaluation workflows
- Full-stack interfaces for AI-assisted geospatial tools
04
Healthcare AI & Research
Contributed to AI research projects involving medical imaging and NLP.
- DCGAN-based augmentation for limited-data medical imaging
- Early HCC detection experiments
- NLP news classification pipeline
- Systematic feature/model iteration and experiment tracking
Experience
Where I have worked
CodeMiner
AI/Backend Engineer, Legal AI & Computer Vision
- Turkish legal AI platform with cited real-time answers
- RAG pipelines over legislation and case law
- Scraping, ingestion, embeddings, semantic chunking and Qdrant indexing
- FastAPI backend architecture and production deployment
- Real-time marina vessel tracking with detection, segmentation and tracking pipelines
UDENE / Horizon Europe Now
ML Engineer & Full-Stack Developer
- EO/GIS segmentation workflows
- Remote-sensing data processing
- Google Earth Engine experimentation
- FastAPI + UI integration for tool-routing LLM workflows
TOBB ETÜ
Research Assistant, AI & Computer Vision
- Medical imaging and data augmentation
- DCGAN-based synthetic data experiments
- NLP classification pipelines
- Reproducible experimentation and student mentoring
Schneider Electric
Data & Business Analyst / Tableau Developer
- KPI dashboards
- Automated reporting workflows
- Data analysis and business intelligence support
JotForm
Data Science Intern
- Fraud-detection workflows
- Transformer-based NLP approaches
- REST API supported scoring workflows
Microsoft
IMAGINE Ambassador, Data Science & AI
- Selected for Azure/AI-focused training; supported community learning and peer mentoring
Education
TOBB University of Economics and Technology
B.Sc. in Artificial Intelligence Engineering · Medium of instruction: 100% English
Publications & presentations
Papers and talks
Deep learning framework for urban seismic risk assessment: two-phase similarity algorithm for damage prediction and loss estimation
SPIE FST 2025 · Oral presentation
From spectral indices to actionable insights: sensitivity analysis of a multispectral U-Net for spatially optimized urban heat island mitigation
SPIE FST 2025
Harnessing EO and Natural Experiments for Urban Development: The UDENE Approach
GeoVISIONS 2025
Developing a Virtual Laboratory for Climate Adaptation with the AI-Powered UDENE Tool
IAF GLOC 2026 · Accepted
Open source
Public projects on GitHub
wahap3
Final project of Digiathon 2022, the TR Presidency Digital Transformation Office competition.
SCSS
DigitDetect
The Intelligent Stack: React, Axios & FastAPI.
JavaScript
steganographywithsift
Steganography with the Scale-Invariant Feature Transform, implemented in Python.
Python
SteamDataHarvester
Multi-threaded scraper for Steam user data that walks user networks and avoids duplicates.
Python
titanicAI
A cruise reservation app that uses AI to predict passenger survival on the Titanic; React, Axios & FastAPI.
JavaScript
earthquakeML
Earthquake damage prediction with machine learning.
Jupyter Notebook
Contact
Let's build something usable.
Send a message with the form, or reach me directly: