Skip to content
View krlov's full-sized avatar

Block or report krlov

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
krlov/README.md

Hi there, I'm Emir Kaan SAIT 👋

🎓 M.Sc. student in Computer Engineering at Yıldız Technical University
🤖 Interested in Artificial Intelligence, Machine Learning, Deep Learning and NLP
🧠 Working on LLM fine-tuning, knowledge distillation, reward engineering and computer vision projects
📍 Istanbul, Turkey


About Me

I have a background in Mechatronics Engineering and I am currently pursuing my Master's degree in Computer Engineering.

My interests mainly focus on:

  • Machine Learning
  • Deep Learning
  • Natural Language Processing (NLP)
  • Computer Vision
  • Large Language Models (LLMs)
  • Representation Learning
  • Ensemble Learning

I enjoy developing AI systems for real-world problems and building technically detailed, research-oriented projects.


Technical Skills

Languages

  • Python
  • C
  • C#
  • SQL

AI / ML

  • PyTorch
  • TensorFlow
  • scikit-learn
  • Hugging Face Transformers
  • LoRA
  • Quantization
  • CNN Architectures
  • Transformer Architectures

Data Science

  • NumPy
  • Pandas
  • Matplotlib
  • PCA
  • Feature Engineering
  • Clustering
  • Representation Analysis

Tools

  • Git
  • Jupyter Notebook
  • VS Code
  • Google Colab

Featured Projects

🔹 Turkish LLM Distillation

Teacher–student distillation pipeline for Turkish multiple-choice question answering using LoRA fine-tuning and ensemble learning.

🔹 GRPO Reward Engineering

Behavioral analysis and model merging experiments for Turkish GPT-2 based question answering systems.

🔹 Welding Defect Classification

Lightweight CNN-based industrial welding defect classification using the RIAWELC dataset.

🔹 Thesis Year Prediction

Embedding-based semantic representation analysis using ensemble regression methods.

🔹 Customer Segmentation

RFM analysis and K-Means clustering on the Online Retail II dataset.


Currently Learning

  • FastAPI
  • Model Deployment
  • Inference Optimization
  • Docker for ML Systems
  • Production-oriented ML pipelines

Contact

📧 emirkaansait@hotmail.com

🔗 LinkedIn
https://www.linkedin.com/in/emir-kaan-sait/

💻 GitHub
https://github.com/krlov

Pinned Loading

  1. online-retail-rfm-segmentation online-retail-rfm-segmentation Public

    Customer segmentation using RFM analysis, K-Means clustering, Elbow/Silhouette evaluation and PCA visualization on the Online Retail II dataset.

    Python

  2. riawelc-welding-defect-classification riawelc-welding-defect-classification Public

    Lightweight CNN-based welding defect classification on the RIAWELC dataset using a customized SqueezeNet architecture.

    Jupyter Notebook

  3. thesis-year-prediction-ensemble thesis-year-prediction-ensemble Public

    Embedding-based thesis year prediction using ensemble regression methods and representation analysis.

    Jupyter Notebook

  4. turkish-grpo-reward-ensembles turkish-grpo-reward-ensembles Public

    Reward engineering, GRPO fine-tuning and model merging for Turkish multiple-choice question answering with GPT-2-based language models.

    Jupyter Notebook

  5. turkish-llm-distillation turkish-llm-distillation Public

    LLM distillation and ensemble learning for Turkish multiple-choice question answering using LoRA fine-tuning and Hugging Face Transformers.

    Jupyter Notebook