Skip to content
View Md-Emon-Hasan's full-sized avatar
:atom:
:atom:
27 followers · 3 following

Achievements

Achievement: StarstruckAchievement: QuickdrawAchievement: Pull SharkAchievement: YOLO

Achievements

Achievement: StarstruckAchievement: QuickdrawAchievement: Pull SharkAchievement: YOLO

Highlights

  • Pro

Block or report Md-Emon-Hasan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Md-Emon-Hasan/README.md

Hello, I am Emon Hasan

Hi there 👋 I am Emon Hasan

Machine Learning Engineer • LLM Fine-Tuning Specialist • Data-driven AI Engineer • Agentic AI Systems Architect

Designing data-centric AI systems, fine-tuning large language models, and deploying production-grade intelligent systems.

💫 About Me:

Hi, I am Md Emon Hasan from Bangladesh. I am a full-stack, end-to-end AI/ML & Agentic AI engineer with comprehensive experience in designing, implementing, and deploying production-ready, multi-agent AI systems. My work spans the entire AI/ML lifecycle, including data collection, preprocessing, feature engineering, model development, fine-tuning (QLoRA / LoRA / PEFT / SFT), evaluation, and scalable deployment.

I specialize in integrating AI/ML models into real-time, tool-augmented, and scalable applications, leveraging multi-agent architectures, LangGraph/AgentOps orchestration, and intelligent reasoning workflows. With a solid foundation in both front-end and back-end development, I ensure AI solutions are not only high-performing but also reliable, maintainable, and enterprise-ready.

My work centers on developing intelligent, adaptive, and real-world AI systems that deliver measurable impact through efficient design, reliable execution, and scalable architecture.

🌐 Socials:

Portfolio LinkedIn Medium WhatsApp Email Twitter Instagram Facebook

🛠️ Tech Stack

💻 Core Languages

Python C++ Java JavaScript TypeScript SQL Bash

🧠 Machine Learning (Classical ML)

Scikit-learn Optuna GridSearchCV RandomizedSearchCV StandardScaler One--Hot--Encoding Boosting Stacking Cross--Validation Stratified--KFold ROC--AUC F1--Score SHAP LIME Regularization Feature--Selection Data--Leakage Overfitting Underfitting

🧠 Deep Learning

PyTorch TensorFlow Keras CNN RNN LSTM GRU Dropout BatchNorm ReLU MSE Adam Backpropagation Learning--Rate Early--Stopping Transfer--Learning Sequence--Modeling TensorBoard

🧠 NLP & Representation Learning

NLTK spaCy Transformers SentenceTransformers TF-IDF Word2Vec FastText Tokenization BPE Lemmatization NER Attention Seq2Seq Semantic--Search Embeddings BLEU ROUGE

🤖 Artificial Intelligence & Agentic AI

LangChain LangGraph LangSmith AgentOps RAG Prompt Engineering Tool Calling LlamaIndex CrewAI AutoGen Multi-Agent Systems Agent Orchestration Planning Reasoning ReAct Memory Long-Term Memory Tool Router Fallback

🔥 LLM Fine-Tuning & Training

PEFT LoRA QLoRA SFT TRL Tokenizers Datasets Instruction--Tuning Fine--Tuning RLHF DPO Mixed--Precision Gradient--Accumulation Quantization Checkpointing Inference--Optimization vLLM Evaluation Perplexity

🧠 Vector Databases & Retrieval

FAISS Chroma Weaviate Pinecone Milvus Qdrant Redis

📊 Data Science & Analysis

NumPy Pandas Matplotlib Seaborn Plotly EDA Statistical Analysis Hypothesis Testing Correlation Data Cleaning Data Wrangling Data Visualization Interactive Visualization Time Series Analysis Feature Engineering Data Pipeline ETL Data Validation Big Data

🗄️ SQL & Databases

MySQL PostgreSQL SQLite Supabase MongoDB Neo4j

⚙️ Backend & APIs

FastAPI Flask REST API Postman WebSockets AsyncIO JWT OAuth2

🌐 Frontend

React Vite TailwindCSS DaisyUI Bootstrap HTML5 CSS3 JavaScript

🚀 Deployment, MLOps & AgentOps

Docker Compose Jenkins CircleCI GitLab CI Monitoring Logging

📊 GitHub Stats:

Gɪᴛʜᴜʙ Sᴛᴀᴛs

GitHub Stats

Sᴛʀᴇᴀᴋ Sᴛᴀᴛs

Streak Stats

Tᴏᴘ Cᴏɴᴛʀɪʙᴜᴛɪᴏɴs

Top Repo

Lᴀᴛᴇsᴛ Pʀᴏᴊᴇᴄᴛ

Awesome-Dev-Portfolios


🏆 GitHub Trophies

GitHub Trophies

✍️ Random Dev Quote

📈 Cᴏɴᴛʀɪʙᴜᴛɪᴏɴ Gʀᴀᴘʜ

Buy Me A Coffee

Pinned Loading

  1. AutoDocThinker AutoDocThinker Public

    Agentic AI system that allows users to upload documents (PDFs, DOCX, etc.) and natural language questions. It uses LLM-based RAG to extract relevant information. The architecture includes multi-age…

    Python 1

  2. InformaTruth InformaTruth Public

    Fine-tuned roberta-base classifier on the LIAR dataset. Aaccepts multiple input types text, URLs, and PDFs and outputs a prediction with a confidence score. It also leverages google/flan-t5-base to…

    Jupyter Notebook 1 1

  3. MediGenius MediGenius Public

    Advanced multi-agent Medical AI Assistant powered by LangGraph that delivers empathetic, doctor-like responses using a hybrid pipeline of LLM reasoning, RAG from medical PDFs, and intelligent fallb…

    Jupyter Notebook 19 6

  4. Translatica Translatica Public

    Spanish literary translation system, fine-tuned using PEFT with LoRA for high accuracy and minimal compute cost. Built with an intuitive, premium-grade web interface with FastAPI, Bootstrap andcust…

    Jupyter Notebook 1

  5. TrueWealth-AI TrueWealth-AI Public

    An intelligent financial advisor chatbot powered by LLaMA-3, built with LangGraph for structured reasoning, RAG from The Intelligent Investor PDF, and real-time data from Yahoo Finance and DuckDuck…

    Jupyter Notebook 5 1

  6. BookSage-AI BookSage-AI Public

    Full-stack hybrid book recommendation system combining Collaborative Filtering and Content-Based Filtering with weighted hybrid scoring, modular data pipelines, and model persistence. Deployed via …

    Python 15 5