Md. Aber Islam

AI/ML Engineer

About Me

I am Md. Aber Islam, an AI and Machine Learning Engineer with a passion for building end-to-end AI solutions that solve real-world problems. With hands-on experience in developing NLP pipelines, fine-tuning Transformer models, and designing scalable AI systems, I specialize in creating intelligent automation for data-driven applications. My expertise spans across Python, PyTorch, FastAPI, LangChain, and more.


I have hands-on experience with NLP projects, including building comprehensive ML pipelines and Bangla NLP applications.

Languages

Python SQL Ruby HTML CSS

Technologies

PyTorch NumPy Pandas Sklearn HuggingFace FAISS FastAPI Docker LangChain

Specializations

Machine Learning NLP AutoML RAG Systems Fine-tuning Computer Vision

Featured Projects

Medical Guideline RAG System

An AI-powered medical consultation system providing evidence-based medication guidance using RAG architecture with comprehensive drug interaction analysis across 33 medical domains. Processed 50,000+ medical articles with <200ms search latency.

FastAPI FAISS Gemini AI NetworkX Streamlit

Real-time Face Mask Detection

A computer vision system detecting face masks in real-time video streams with 96% accuracy using PyTorch and MobileNetV3 architecture. Supports multiple input types including live camera feeds.

PyTorch MobileNetV3 Computer Vision Gradio

Real-time News Sentiment Dashboard

A real-time dashboard monitoring news headlines with instant sentiment classification. Processes 100+ headlines per minute with 96% accuracy using Hugging Face Transformers and FastAPI.

HuggingFace FastAPI NLP RSS Feeds

AutoML AI Assistant Usage Prediction

An automated ML system predicting students' AI assistant usage patterns using PyCaret. Processed 10,000+ interaction records with 90% prediction accuracy, reducing ML workflow time significantly.

PyCaret AutoML Data Science Educational AI

Experience

Machine Learning Intern

Aspire to Innovate (a2i) Program
Jun 2024 - Dec 2024 | Dhaka, Bangladesh
  • Worked at a government initiative developing innovative technology solutions for public services, processing and analyzing datasets while implementing quality assurance protocols for government systems.
  • Developed NLP pipelines for Bangla text classification, achieving high accuracy in sentiment analysis and designed web scraping solutions for Bangladesh's largest open-source Bangla NLP corpus.
  • Engineered automated workflows reducing data preprocessing time and implemented machine learning models for public service optimization analytics.
  • Contributed to building scalable ML infrastructure for government data processing, enabling efficient analysis of large-scale public service datasets for policy decision-making.

Get In Touch

I'm always interested in discussing new opportunities, collaborations, or just chatting about AI/ML. Feel free to reach out!