Skip to content
View arju10's full-sized avatar

Block or report arju10

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.

Content in all repositories owned by your account will be closed.
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
arju10/README.md

Hi, I'm Tahmina Jerin Arju πŸ‘‹

Software Engineer specializing in modern web applications and AI-powered systems

πŸ“ Dhaka, Bangladesh (UTC+6)
πŸ“§ mst.tahminajerinarju@gmail.com
πŸ”— Portfolio Β· LinkedIn Β· GitHub


πŸš€ About Me

I'm a Software Engineer with hands-on experience building complete products β€” from clean React/Next.js frontends to scalable Node.js backends, databases, authentication systems, payment integrations, and AI/LLM features.

I enjoy owning features end-to-end: designing APIs, implementing secure auth, integrating vector databases and LLMs, handling deployments, and making sure the final product actually works well for users.

I also have a strong foundation in C, C++, Data Structures, and Algorithms, which helps me write efficient and well-structured code.

During my internships I built a multilingual agricultural chatbot with image-based disease detection, worked on RAG and LLM-based systems, and contributed to a real ERP platform. I also co-authored a research paper on AI chatbot adoption that was published in an international journal.

I'm currently focused on building production-ready full-stack applications and practical AI integrations (RAG, agents, and multimodal systems).


πŸ’Ό Professional Experience

ML Engineer Intern Β· Software Intelligence Ltd.
Feb 2025 – May 2025

  • Built a multilingual Bangla Agricultural Advisor Chatbot supporting text, voice, and image-based crop disease detection
  • Implemented Bengali NLP pipeline, image classification models, Bangla OCR, and embedding-based retrieval with ChromaDB
  • Managed the complete ML pipeline, REST API integration, and model deployment on AWS

AI/ML Researcher Intern Β· Time Research & Innovation
Dec 2024 – Mar 2025

  • Developed LLM-based AI chatbots with interactive features
  • Applied federated learning techniques for privacy-preserving model training
  • Automated data preprocessing pipelines and supported model evaluation & optimization

Software Project Developer Intern Β· Goinnovior Limited
Feb 2024 – Jun 2024

  • Developed a MERN-based ERP system with scalable backend APIs and role-based access control
  • Implemented core business modules and improved overall system performance
  • Collaborated with cross-functional teams on requirement analysis, development, and testing

πŸ› οΈ Featured Projects

🧠 DocuMind AI β€” RAG Document Chat System

Live Demo

An AI-powered web application that lets users upload PDF documents and ask questions in natural language. Instead of manually searching through long files, users get direct answers with source citations.

Key Features:

  • Full RAG pipeline: PDF extraction β†’ chunking β†’ embeddings β†’ semantic search (ChromaDB) β†’ answer generation (Groq Llama 3.3 70B)
  • Source citations so users can verify every answer
  • JWT authentication, password hashing, and protected routes
  • Mobile-responsive UI with drag-and-drop upload and real-time chat

Tech Stack: React, TypeScript, Node.js, Express, MongoDB, ChromaDB, Groq Llama 3.3, Docker


πŸ”§ FixItNow β€” Service Booking Platform

Live Demo Β· Backend

A full-stack platform that connects customers with verified technicians. Users can browse services, book appointments, and pay online in one flow.

Key Features:

  • Role-based access (Customer, Technician, Admin) with dedicated dashboards
  • Secure authentication using NextAuth.js
  • Online payments integrated with Stripe
  • Responsive design built with Next.js and Tailwind CSS

Tech Stack: Next.js, TypeScript, Tailwind CSS, Node.js, Express, MongoDB, NextAuth.js, Stripe


Live Demo Β· Backend

A platform that allows users to check real-time availability of sports facilities and book time slots without double-booking issues.

Key Features:

  • Real-time availability checking
  • Conflict prevention for overlapping bookings
  • JWT authentication and role-based access control
  • Optimized backend queries for better performance

Tech Stack: Node.js, Express, TypeScript, MongoDB


A multilingual chatbot designed to help farmers in Bangladesh. Supports text queries, voice input, and image-based crop disease detection.

Key Features:

  • Bengali language support (text + voice)
  • Image classification for disease detection
  • Advice generation based on detected issues

Tech Stack: Django, TensorFlow, Bengali NLP, OCR


πŸ’» Tech Stack

Languages: JavaScript, TypeScript, Python, C, C++, SQL

Frontend: React, Next.js, Tailwind CSS

Backend: Node.js, Express.js, REST APIs

Databases: MongoDB, PostgreSQL, MySQL, Redis, ChromaDB (Vector DB)

AI / ML: LLMs, RAG, Hugging Face, TensorFlow, Keras, Scikit-learn, LangChain, NLP

Core CS: Data Structures, Algorithms

Tools & DevOps: Git, Docker, AWS, Vercel, Render, CI/CD, Jira


πŸŽ“ Education

MSc in Computer Science
Independent University, Bangladesh
Sep 2024 – Aug 2025

BBA in Management Information Systems (MIS)
Independent University, Bangladesh
May 2019 – Apr 2024
Minor: Big Data and High-Performance Computing


πŸ“„ Research & Publication

Investigating the Factors Affecting the Intention to Use AI Chatbots in STEM Education: A Hybrid SEM and ANN Approach
European Journal of STEM Education, Vol. 11, Issue 1 Β· June 2026 (Co-author)

  • Applied a hybrid SEM + ANN approach to study AI chatbot adoption among students
  • Analyzed ICT self-efficacy, self-directed learning, and perceived ease of use across 117 participants

πŸ“« Let's Connect

I'm open to Full-Stack Engineer and AI Engineering opportunities where I can build useful products and continue growing.

Feel free to reach out via email or LinkedIn.

Pinned Loading

  1. fixitnow fixitnow Public

    FixItNow is a modern, responsive web application built with Next.js 16 (App Router) that connects Customers with verified Technicians for service bookings. This frontend provides a seamless, user-f…

    TypeScript

  2. documind-ai documind-ai Public

    Upload any PDF and chat with it using AI. Powered by RAG, Groq Llama 3, ChromaDB and fully written in TypeScript.

    TypeScript

  3. sports-facility-booking sports-facility-booking Public

    TypeScript

  4. Bangla-Agricultural-Advisor-Chatbot-using-django Bangla-Agricultural-Advisor-Chatbot-using-django Public

    The Bangla Agricultural Advisor Chatbot is a Django-based web application designed to assist farmers and agricultural enthusiasts in Bangladesh by providing advice and solutions in the Bengali lang…

    Python

  5. Event-Ticket-Booking-Management-Platform-Backend Event-Ticket-Booking-Management-Platform-Backend Public

    A production-shaped backend for discovering, booking, and managing event tickets β€” built with Node.js, TypeScript, Express, PostgreSQL, and Prisma 7.

    TypeScript