Md. Ehsanul Haque K. looks like a good fit?

We can organize an interview with Aldin or any of our 25,000 available candidates within 48 hours. How would you like to proceed?

Schedule Interview Now

Md. Ehsanul Haque K. - Fullstack Developer, React Native, nextjs

Being part of Softaims has allowed me to see the full spectrum of what technology can achieve when guided by empathy, discipline, and creativity. Each assignment, regardless of size, represents an opportunity to bring clarity to complexity and to turn ambitious ideas into tangible outcomes. I’ve come to realize that successful development isn’t just about writing code—it’s about listening carefully, understanding deeply, and designing thoughtfully. Every client brings unique challenges, and I make it a priority to align my work with their goals, ensuring that the end result is both effective and lasting. Softaims fosters an environment where collaboration is not optional—it’s essential. The collective expertise within the team pushes me to think beyond conventional boundaries, to question, refine, and innovate. I believe that this process of shared learning and experimentation is what makes our solutions resilient and impactful. My ultimate goal is to build technology that feels effortless to use yet powerful in function. I approach every task with the mindset that small details can make a big difference. Through continuous refinement and dedication, I aim to contribute to the kind of work that not only serves today’s needs but anticipates tomorrow’s possibilities.

Main technologies

  • Fullstack Developer

    14 years

  • React

    12 Years

  • Django

    11 Years

  • HTML5

    3 Years

Additional skills

  • React
  • Django
  • HTML5
  • On-Page SEO
  • Technical Writing
  • Yoast SEO
  • Blog Writing
  • Machine Learning
  • Mobile UI Design
  • User Experience Design
  • Google Cloud
  • React Native
  • nextjs

Direct hire

Potentially possible

Ready to get matched with vetted developers fast?

Let’s get started today!

Hire undefined

Experience Highlights

RescueVision: AI-Powered Search & Rescue Command Center

I built RescueVision, an end-to-end, multi-modal AI system to accelerate search and rescue (SAR) operations. I trained a YOLOv8n object detection model on over 2,200 aerial images, achieving a Precision of 85.3%, Recall of 76.2%, and mAP50 of 0.833. The system also includes a private RAG pipeline built with LangChain and ChromaDB. The entire project was developed with a robust microservices architecture, integrating Flask-based AI services with a React/TypeScript frontend.

AI-Powered Customer Feedback Platform

Built an end-to-end, full-stack platform to transform unstructured customer feedback into actionable business intelligence. I developed an advanced Retrieval-Augmented Generation (RAG) pipeline using Sentence-Transformers for embeddings and a persistent ChromaDB knowledge base (10,000+ items). The platform features Intelligent Document Processing with LLM-based chunking and Tesseract OCR for comprehensive data ingestion (.pdf, .docx). The Groq LPU-powered LLaMA 3 model provides high-speed conversational analysis (average time-to-first-token <150ms).

Prescriptive Maintenance System (ML, LLM, RAG, NLP)

I built a Prescriptive Maintenance system that goes beyond prediction by using a Retrieval-Augmented Generation (RAG) pipeline to prescribe solutions via a conversational AI assistant. It includes an end-to-end MLOps lifecycle, a Human-in-the-Loop (HITL) framework, and Docker containerization. I achieved an RMSE of 15.82 and 95% Recall. The system's private RAG pipeline uses Ollama, ChromaDB, and LangChain.

AuraScanAI: AI-Powered Vehicle Damage Assessment System

I built AuraScanAI, an end-to-end computer vision system demonstrating a full MLOps lifecycle for vehicle damage assessment. I custom-trained a Vision Transformer (ViT) on over 15,500 images, fine-tuning a vit_base_patch16_224 model to achieve a best validation loss of 248.27. The system features a professional MLOps workflow using Docker and Git LFS for model management, and a full-stack architecture with a Flask/PyTorch API on Hugging Face Spaces and a React/TypeScript frontend on Vercel. The backend also includes a Business Rule Engine for severity classification and repair costs.

AI Research Assistant (Local LLM & RAG Agent)

Developed a full-stack, end-to-end AI agent capable of answering complex questions with up-to-date, sourced information. This project utilizes modern AI agent architecture, achieving a 100% task success rate and 67% faster responses by leveraging a robust, orchestrated Retrieval-Augmented Generation (RAG) workflow with a local LLM (Phi-3).

Education

  • International University of Business Agriculture and Technology

    Bachelor of Science (BS) in Electrical and Electronics Engineering

    2010-01-01-2014-01-01

Languages

  • English

Personal Accounts