Akgün Software — Software Engineering Intern
- Contributed to backend and API development while supporting frontend implementation tasks.
- Worked with relational databases and SQL queries to support application data operations.
curriculum vitae
Furkan Barış
machine learning for network security
- githubgithub.com/ffurkanbaris
- linkedinlinkedin.com/in/ffurkanbaris
- hacktheboxprofile.hackthebox.com
- email[email protected]
download pdf ↓ · or print this page
01
summary
Final-year computer engineering student working on machine learning for cybersecurity: one-class anomaly detection on medical-device network traffic, multimodal phishing detection, and retrieval-augmented generation. Comfortable in PyTorch and FastAPI, on real datasets, with results I can reproduce.
Seeking a mandatory internship — 40 business days, insurance covered by the university — in cybersecurity, machine learning, data engineering, or software development. Available in Istanbul, Ankara, Izmir, or remotely.
02
experience
03
education
Karadeniz Technical University
- B.S. in Computer Engineering.
- All coursework completed; graduation pending completion of the mandatory internship.
04
selected work
anomaly-detection
one-class intrusion detection for IoMT network traffic (thesis)
- Developed a CNN-DROCC one-class model for anomaly detection in Internet of Medical Things network traffic.
- Achieved 0.92 accuracy on CIC-IoMT-2024 and 0.97 on WUSTL-EHMS-2020.
PyTorch · CNN-DROCC · Python · CIC-IoMT-2024 · WUSTL-EHMS-2020
phishfusion
multimodal QR code phishing detection
- Engineered a three-branch neural network combining a Transformer lexical encoder with URL and QR structural features.
- Achieved 0.96 binary classification accuracy on an imbalanced phishing dataset.
PyTorch · Transformer · MLP · Cross-Modal Attention
docrag
multi-user document RAG platform
- Built a multi-user document RAG application with secure PDF, DOCX, and URL ingestion; hybrid retrieval, reranking, and source-cited Gemini responses.
- Implemented JWT authentication, capsule-level data isolation, background ingestion workers, persistent chat history, automatic capsule summaries, and continuation handling for long LLM outputs.
FastAPI · PostgreSQL · Redis · Qdrant · Gemini · Google Cloud
05
skills
- languages
- Python · C · C++ · Bash · Java · SQL · JavaScript
- ml / deep learning
- PyTorch · CNNs · Transformers · MLPs · LLMs
- data & analysis
- NumPy · Pandas · scikit-learn
- security & networks
- Wireshark · Burp Suite · Metasploit · Nmap
- devops & tools
- Git · Docker · Linux
- turkish
- Native
- english
- B2