Selen Akkaya
Ai & Ml Engineer @Zirak
Signup · Get unlimited contacts
WORK HISTORY
Ai & Ml Engineer @Zirak
I build AI solutions at the intersection of computer vision and satellite imagery analysis, with a strong focus on scalable machine learning pipelines and deep learning for Earth observation.My experience spans- High-resolution satellite data (PlanetScope 8-band), developing end-to-end pipelines for land cover classification, algae detection, vegetation index computation (NDVI, NDWI, SAVI, GCVI), and change detection- Geospatial data engineering, integrating tools like Rasterio, GDAL, and Geopandas into efficient processing workflows- 3D point cloud analysis, designing object detection and semantic segmentation models for complex multi-domain applications.Robust ML engineering practices, proficient in Python, deep learning architectures, Random Forests, version control, testing, containerization, and model deployment.I thrive on turning raw geospatial data into tangible insights and operational intelligence, whether for environmental monitoring, agriculture, or large-scale automation.
EDUCATION
Politecnico di Torino
Master's degree, AI and Data Analytics (Computer Engineering)
Antalya Bilim University
Bachelor's degree, Computer Engineering
Antalya Bilim University
English Preparatory Year
ABOUT SELEN AKKAYA
I work at the intersection of Computer Vision, Deep Learning, and Language Models, building AI systems for satellite and remote sensing data. I have hands-on experience with high-resolution multispectral imagery, applying deep learning to land cover classification, segmentation, and object detection.Alongside computer vision, I develop LLM and Retrieval-Augmented Generation (RAG) pipelines for document analysis, semantic search, and interactive Q&A. My stack includes Python, PyTorch, TensorFlow, geospatial libraries (Rasterio, GeoPandas), and modern LLM tooling.I’m motivated to contribute to impactful AI projects across Earth Observation, sustainability, and intelligent data systems
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.