AI Engineer · Tashkent, Uzbekistan
I'm Javohir — an AI engineer who turns messy, real-world problems into production systems. Currently shipping a medical consultation platform at SinoAI.
About
From custom medical RAG pipelines to real-time voice consultation over WebSocket, I care about the full arc of a product — not just the model. That means evaluation, observability, deployment, and the team workflow around it.
My background spans data science internships, e-commerce analytics, and production AI engineering. I like working at the intersection of research and reality — where a paper becomes a feature a user actually touches.
Experience
Selected projects
End-to-end health monitoring: Samsung Galaxy Watch (Wear OS) → Android app → FastAPI backend with ML-based ECG classification. Collects 8 biometric signals and runs 1D-CNN, XGBoost, and SVM models for 5-class arrhythmia detection on live ECG.
Breast ultrasound analysis with an EfficientNet-B0 3-class classifier and a U-Net + ResNet-34 segmentation head. Full-stack web app with FastAPI backend and a React frontend featuring drag-and-drop upload and tumor overlays.
Merged 6 financial data sources into a unified 90K-record, 85-feature dataset. Engineered 27 domain features and built a LightGBM pipeline with class-weighted training for imbalanced default prediction.
Analyzes human emotion from images, video streams, and text using CV and NLP. Recognizes happiness, sadness, anger, surprise, and neutrality across modalities.
Stack
Opinionated about production, pragmatic about everything else.
Contact
Collaborations, research, or a quick hello — I'd love to hear from you.