About

About

Hello, I am Emirhan YILDIRIM.

Machine Learning Engineer and M.Sc. student (Sakarya University) focused on Computer Vision, LLM/RAG Systems, and MLOps.

I build ML systems that keep working after the demo: containerized, tested, drift-aware. Medical AI models break on another lab’s camera, so a good part of my work is about making them hold up on data they were not tuned for.

What I Have Built

  • WBC Analyzer - blood-cell classifier at 98.53% in-distribution accuracy. Inference-time domain adaptation (Reinhard normalization, TTA, binary routing) raised accuracy on an unseen-hardware, two-class OOD set from 56.96% to 89.05% (+32.09 pp) with no retraining. Preprint on ResearchGate, live demo.
  • RAG Project Assistant - ChromaDB + Groq Llama 3.3 70B behind a FastAPI service on Hugging Face Spaces, with a similarity-threshold gate and IP rate limiting. It answers questions about my projects in the chat widget on this site.
  • Kinematic Action Recognition - pipeline over 10 GB of motion-capture data: 0.9995 Macro F1 on the binary subset, 81 windows/sec streaming in 59 MB peak RAM with ADWIN drift detection, 0.94169 private leaderboard accuracy on the Kaggle variant.
  • Automation in production - Listing Pilot and Portal Cleaner Ultimate cut manual workloads by 90%+. The zidorun backend has handled ~1,000 transactions at a 95%+ success rate.

Current Research

  • Computer Vision & Machine Learning Research Project (Sakarya University, Aug 2026 - Present) - supervised research continued as my M.Sc. thesis: real-time video processing with a focus on low latency and temporal consistency. Details and results are withheld at my supervisor’s request until publication.
  • Computer Vision for Blood Cell Microscopy (Sakarya University, Sep 2026 - Present) - an image processing toolkit for stained blood smear microscopy, from raw microscope images to quantitative cell measurements: stain normalization, nucleus and cell segmentation, texture and shape features, validated against expert annotations.

Experience

  • Software Engineer Intern - Esbi Bilişim ve Telekomünikasyon (Jul 2026 - Aug 2026): CRM web application in ASP.NET Core MVC and Entity Framework Core, with role-based authentication (ASP.NET Core Identity) and customer and inventory modules.
  • Software Engineer & Founder - zidorun (Jun 2025 - Present): backend and automation for a physical collectibles business, including Listing Pilot.
  • Software Engineer Intern - Platech Coating (Jun 2025 - Jul 2025): Portal Cleaner Ultimate, which took daily ERP processing from 4-6 hours to under 30 minutes and stayed in production use after the internship.

Education

  • M.Sc., Information Systems Engineering - Sakarya University (Sep 2026 - Feb 2028). Focus: Medical AI, Computer Vision, Machine Learning.
  • B.Sc., Information Systems Engineering - Sakarya University (Sep 2021 - Sep 2026).

Tech Stack

  • Programming: Python, SQL, C#
  • ML & Computer Vision: PyTorch, TensorFlow, Keras, Scikit-Learn, OpenCV, LightGBM; CNNs, domain adaptation, Grad-CAM explainability
  • LLM & RAG: ChromaDB, Sentence Transformers, Groq API, RAG pipeline design, hallucination suppression
  • MLOps & Deployment: Docker (multi-stage builds), GitHub Actions CI/CD, FastAPI, Flask, Hugging Face Spaces, ADWIN drift detection
  • Backend & Data: ASP.NET Core MVC, Entity Framework Core, Dask, Pandas, NumPy, REST APIs

Languages

  • Turkish: Native
  • English: Professional working proficiency (YOKDIL: 91.25/100, Aug 2026)

Certifications

  • Machine Learning Specialization - DeepLearning.AI / Stanford University (Aug 2026)
  • CS50x: Introduction to Computer Science - Harvard University (May 2025)
  • Odoo Student Diploma - Odoo (Dec 2025)
  • Completed courses: Unsupervised Learning, Recommenders, Reinforcement Learning (Aug 2026); Advanced Learning Algorithms (Jul 2026); Supervised Machine Learning: Regression and Classification (Jun 2026) - DeepLearning.AI

Location

  • Sakarya, Türkiye (remote or on-site in Sakarya)

Contact

Open to Machine Learning, Computer Vision and AI Engineer roles, remotely or hybrid / on-site near Sakarya. Available part-time or as an intern alongside my M.Sc. studies.