Hi, my name is

Omar Madjitov.

I build reliable software and data systems that others can reason about and extend.

React / Next.js / TypeScript
Python / ML / Data Science
PostgreSQL / Supabase / AWS
Production Apps Deployed
Scroll

Featured Work

Selected Projects

demoData

Geospatial Revenue Analytics

End-to-end analytics pipeline converting raw QuickBooks exports into geospatial and time-series analysis, deriving sales territories and revenue insights.

  • 65% high-confidence customer geolocation coverage
  • Derived 6 sales territories capturing 75% of revenue
PythonPandasGeoPandasSQL+1
2025-092025-12
liveFull Stack

Job Ledger

A full-stack job application tracking platform with user-scoped CRUD, analytics dashboards, and external job-feed ingestion.

  • Full-stack job tracking platform with JWT authentication
  • Analytics dashboards improving organization efficiency by 25-40%
ReactViteExpressPostgreSQL+1
2025-102025-12
demoML/AI

Brain Tumor Detection (YOLOv8)

Medical imaging object detection system using YOLOv8 for brain tumor detection, achieving 0.905 mAP@50 with reproducible training pipelines.

  • Achieved mAP@50 = 0.905, IoU = 0.73, pixel accuracy = 0.91
  • Diagnosed dataset-label mismatch and reframed the problem
PythonPyTorchYOLOv8NumPy+1
2025-092025-11
liveWeb App

Seven Lines Corporate Website

Modern, responsive corporate website for a logistics company built with Next.js App Router, featuring mobile-first design and optimized performance.

  • Modern responsive corporate website with Next.js App Router
  • Mobile-first layout with optimized asset loading
Next.jsTypeScriptTailwind CSS
2024-072025-09
liveFull Stack

HandyHub

A community-driven Q&A platform with user authentication, voting, rewards, and threaded discussions supporting 50K+ monthly active users.

  • Community Q&A platform with 50K+ monthly active users
  • Authentication, voting, rewards, and threaded discussions
ReactTypeScriptSupabaseTailwind CSS
2025-062025-08
demoData

Housing Price Drivers Analysis

Urban data science study analyzing how school quality and crime rates influence housing prices, achieving 95% F1-score with Random Forest models.

  • Led 6-person team analyzing 30K+ records
  • Achieved 95% F1-score for price-category prediction
PythonScikit-learnPandasNumPy+1
2025-012025-05

What I Work With

Skills & Technologies

Frontend

  • React.js
  • Next.js
  • TypeScript
  • Tailwind CSS
  • HTML/CSS

Backend

  • Node.js
  • Express.js
  • Python
  • PostgreSQL
  • REST APIs

Data & ML

  • Pandas
  • NumPy
  • Scikit-learn
  • PyTorch
  • TensorFlow

Cloud & DevOps

  • AWS
  • Supabase
  • Docker
  • Git/GitHub
  • CI/CD

Get In Touch

Let's work together

I'm seeking roles where I can build software people rely on, collaborate with experienced teammates, and help ship real products. If that sounds like your team, let's connect.

Say Hello