Skip to content
View furk4neg3's full-sized avatar
🎯
Focusing
🎯
Focusing
8 followers · 5 following

Achievements

Achievement: Pull SharkAchievement: YOLO

Achievements

Achievement: Pull SharkAchievement: YOLO

Highlights

  • Pro

Block or report furk4neg3

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
furk4neg3/README.md

Hi there, I'm Furkan Egecan Nizam 👋

AI Engineer | Systems Engineer

I am a Computer Engineering student at Gazi University (ranked 1st in my department out of 120 students) and currently work as a Systems & Reliability Engineering Trainee at Turkish Aerospace (TAI - TUSAŞ). I specialize in building highly optimized deep learning architectures, developing lightweight MLOps tools, and solving complex, system-wide architectural bottlenecks.

🛠️ Core Tech Stack

  • Languages & Architecture: Python, C#, SQL, System Architecture, Docker
  • AI & Machine Learning: PyTorch, TensorFlow, CNNs, Vision Transformers (ViT), Federated Learning
  • NLP & Backend: GPT APIs, LLM Fine-Tuning, Hugging Face Transformers, FastAPI, Flask

🚀 Featured Projects

  • DriftSense: A lightweight, Docker-first MLOps CLI tool for tabular pipelines that detects data and concept drift using statistical tests (KS, PSI, ADWIN) with built-in Slack/SMTP alerting.
  • High-Dexterity Prosthetic Hand (sEMG Deep Learning): A custom Domain-Adversarial Neural Network (DANN) for sEMG gesture classification. Achieved 87.7% validation accuracy via per-subject fine-tuning and slashed training time by 80% using XLA JIT compilation.
  • MeldFlow: A multi-modal ML toolkit (vision, tabular, text) built with PyTorch and Hugging Face, enabling rapid training and deployment via a FastAPI inference server.
  • FedChain: A privacy-preserving federated learning system secured on an Ethereum blockchain, utilizing smart contracts for immutable auditability of model weight updates.

📫 Let's Connect

Pinned Loading

  1. jotform-ai-agent-autotest jotform-ai-agent-autotest Public

    Instantly validate Jotform AI Agent updates with GPT-powered auto-previewing tools

    TypeScript 1

  2. FedChain FedChain Public

    A privacy-preserving federated learning framework integrated with blockchain to ensure decentralized training, secure model updates, and trustless collaboration.

    Python 1 1

  3. DriftSense DriftSense Public

    Production-ready concept & data drift monitoring with auto-retraining, model versioning, Docker, CI, alerts, and a synthetic 30-day stream.

    Python 1

  4. MeldFlow MeldFlow Public

    Train & serve multi-modal ML (images + tabular + text) with configurable encoders/fusion, FastAPI inference, Docker-first quickstart, and make test.

    Python 1

  5. Traffic-Volume-Forecasting Traffic-Volume-Forecasting Public

    Traffic volume forecasting with AI using bidirectional LSTM model and React frontend.

    Python 2

  6. ViNET ViNET Public

    Forked from xddlzx/ViNET

    An offline, real-time iOS app that empowers visually impaired users with instant object detection and depth estimation via speech and haptic feedback.

    Swift