Profile banner
Shahariar Rabby

Shahariar Rabby

CS PhD & Machine Learning Engineer who builds and deploys production-ready computer vision systems

shahariar-rabby
Birmingham, Alabama
Joined May 2025
Favicon imagerabby.dev
Favicon imagegithub.com
Favicon imagex.com

Network

648 connections
🔬
Academic Researchers & PhDs
🤖
AI/ML Engineers & Scientists
🌼
Daffodil University Affiliates
💡
Startup Founders & Entrepreneurs
🎓
UAB Academic Faculty & Researchers
📚
UAB PhD Students & Postdocs
🎯
AI Strategy & Innovation Leaders

Summary

Shahariar Rabby is a highly skilled Machine Learning Engineer and CS PhD candidate specializing in production-ready computer vision and deep learning systems. His expertise spans the full ML lifecycle, from model development using PyTorch and TensorFlow to deployment with Docker, FastAPI, Flask, and AWS. He has applied his skills to various domains, including 3D medical imaging and OCR, with notable achievements in COPD prediction and pulmonary fissure segmentation. rabby+2
Rabby has a strong background in academic research, particularly in the fields of Computer Vision, Deep Learning, and Natural Language Processing. He is a Ph.D. Candidate at the University of Alabama at Birmingham and a Graduate Research Assistant at the CLAIR lab, where he contributes to NIH and NSF-funded projects. His Google Scholar profile lists numerous publications with significant citations, reflecting his contributions to areas like Bangla handwritten character recognition, sign language datasets, and neural radiance fields. google+1
He is a recognized innovator in low-resource language processing, evidenced by his leadership in developing "Ekush," the largest Bangla handwritten dataset, which has received national and international accolades. He also co-founded and supervised the Computational Intelligence LAB (CI LAB) and DIU - NLP and Machine Learning Research LAB, showcasing his commitment to advancing AI in underserved linguistic contexts. rabby+2
Shahariar Rabby has practical industry experience, including roles as a Machine Learning Engineer and Team Lead (ML) at Apurba Technologies, where he significantly improved OCR accuracy. His work there involved delivering end-to-end ML projects and mentoring junior engineers, demonstrating his ability to translate complex research into scalable and impactful solutions. rabby+1

Work

Education

Projects

Writing

COPDxNet: Accurate and Explainable Prediction of COPD from Low-Dose CT Scans using Deep Learning

July 1, 2025

A pre-print paper describing a deep learning model for accurate and explainable COPD prediction from low-dose CT scans.

Favicon imagemedrxiv.org

BeyondPixels: A comprehensive review of the evolution of neural radiance fields

January 1, 2023

A comprehensive review discussing the evolution of neural radiance fields.

Favicon imagescholar.google.com

A Study on Dengue Fever in Bangladesh: Predicting the Probability of Dengue Infection with External Behavior with Machine Learning

January 1, 2021

A study using machine learning to predict the probability of dengue infection in Bangladesh.

Favicon imagescholar.google.com

Abstractive method of text summarization with sequence to sequence RNNs

January 1, 2019

A paper exploring abstractive text summarization using sequence-to-sequence RNNs.

Favicon imagescholar.google.com

BornoNet: Bangla Handwritten Characters Recognition Using Convolutional Neural Network

January 1, 2018

A research paper on recognizing Bangla handwritten characters using CNNs.

Favicon imagescholar.google.com

Ekush: A Multipurpose and Multitype Comprehensive Database for Online Off-Line Bangla Handwritten Characters

January 1, 2018

A paper describing the Ekush dataset for Bangla handwritten characters.

Favicon imagescholar.google.com

Ishara-Lipi: The First Complete MultipurposeOpen Access Dataset of Isolated Characters for Bangla Sign Language

January 1, 2018

A paper on the first complete multipurpose open-access dataset for Bangla Sign Language isolated characters.

Favicon imagescholar.google.com

EkushNet: Using Convolutional Neural Network for Bangla Handwritten Recognition

January 1, 2018

A paper on using Convolutional Neural Networks for Bangla handwritten recognition.

Favicon imagescholar.google.com

Hobbies

Enjoys reading books and watching movies. rabby

Interested in outdoor activities, fieldwork, STEM equity, and science communication. rabby

Likes making computers able to see and talk, a hobby related to his professional work in AI and deep learning. nitter