Nizomiddin Xalilov
Backend & Computer Vision Engineer
Python and Django on the backend, YOLO and OpenCV on the camera side. Today I run the internal platforms of a US-market logistics operation: 500 trucks, 600 trailers, seven live camera feeds and a gate that opens by itself.
Experience
- Trained YOLOv11 models for vehicle type, colour, USDOT, unit and trailer numbers (82–95% accuracy, 1,500+ images) and joined them into automated gate control.
- Moved the fleet and asset teams from Google Sheets to a Django platform: trucks, companies, devices in use, inactive and charges, inspections, trailer agreements.
- Built a safety events dashboard on the Motive API that counts each driver's alerts since the team's last action.
- Automated splitting of trailer toll charges between leasing companies on file upload.
- Analysed US diesel prices and discounts by state and station; built a weekly fleet movement report from the Genlogs API.
- IT support: installed Windows and set up workstations, rolled out Krisp across the carrier sales office, and handled hardware issues.
Selected projects
A YOLOv5 model that finds cancer regions in prostate biopsy images and grades them on the Gleason scale — in about 0.1 s per image.
Seven yard cameras, one pipeline: detect the vehicle, read its USDOT and unit numbers, check the carrier and open the gate.
Eye Aspect Ratio in real time from a webcam. When the eyes stay closed too long, it makes noise.
One system for a restaurant chain: till, kitchen screen, menu and cost price, stock, staff, bookings, loyalty and reports — for every branch.
All 575 trucks on one map, live: where each one is, how fast it moves, and which ones report a fault or low fuel.
Skills
Python, Django, Django REST Framework, PostgreSQL, REST API design, Celery, Redis
YOLOv5 / YOLOv11, OpenCV, PyTorch, MediaPipe, OCR / plate recognition, RTSP stream handling
Pandas, NumPy, SQL optimisation, ETL pipelines
Linux, Docker, Nginx, Gunicorn, Networking / VPN, Windows Server
JavaScript (ES6+), HTML / CSS, Django templates