Skip to content
View AlokTheDataGuy's full-sized avatar
💭
On my way, to become a Kick-ass Data Scientist
💭
On my way, to become a Kick-ass Data Scientist

Block or report AlokTheDataGuy

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
AlokTheDataGuy/README.md

💫 About Me:

Hi, I'm Alok Deep, an MCA Data Science postgraduate and a Full-Stack Developer & AI Engineer. I design and ship end-to-end products — from responsive, production-grade web applications to LLM-powered systems, Retrieval-Augmented Generation (RAG), and intelligent data-driven solutions. I work across the stack with React/Next.js, Node.js, Python, and SQL, turning ideas into live, usable products.


🚀 Skills & Expertise

🌐 Full-Stack Web Development

I build complete, production-ready web applications — designing the UI, wiring up the backend, and deploying live.

  • Frontend: React, Next.js, Tailwind CSS, JavaScript, responsive & component-driven UI
  • Backend: Node.js, Express, FastAPI, Flask — REST APIs & service integration
  • Databases: MySQL, PostgreSQL, MongoDB
  • Deployment & Tooling: Vercel, Render, Docker, Git
  • Focus: Responsive design, cross-browser consistency, performance optimization, clean and maintainable code, SEO

🤖 Artificial Intelligence & Machine Learning

  • Generative AI (LLMs, RAG, Prompt Engineering, Multi-modal AI)
  • NLP: Transformers, BERT, Text Classification, Sentiment Analysis
  • Retrieval Systems: Vector Databases (FAISS, ChromaDB), Semantic Search
  • Time-Series Forecasting, Anomaly Detection
  • Recommendation Systems, Clustering, Segmentation
  • Model Evaluation, Feature Engineering, Optimization

🧠 Machine Learning & Data Science

  • Exploratory Data Analysis (EDA), Statistical Analysis, A/B Testing
  • Predictive Modeling (Regression, Classification, Time Series)
  • Data Cleaning, Feature Engineering, Outlier Detection
  • Experiment design and insight generation

⚙️ AI Systems & Data Engineering

  • End-to-end AI system design (RAG pipelines, LLM integration)
  • ETL Pipelines, Data Processing, Workflow automation
  • API-based ML deployment (FastAPI, Flask)
  • Handling structured + unstructured data systems

🛠️ Tools & Technologies

  • Languages: Python, SQL, JavaScript
  • Web: React, Next.js, Tailwind CSS, Node.js, Express
  • AI/ML: Scikit-learn, TensorFlow, PyTorch, Hugging Face
  • LLM Stack: LangChain, LangGraph, Ollama, Vector DBs
  • Data Engineering: Airflow, Docker
  • Databases: MySQL, PostgreSQL, MongoDB
  • Deployment: Vercel, Render, Docker

💻 Tech Stack:

Python JavaScript React Next.js Tailwind CSS CSS3 Node.js Express.js FastAPI Flask MongoDB MySQL PostgreSQL NumPy Pandas Excel Power BI Tableau Power Query Power Pivot LaTeX Git NLP Computer Vision Scikit-learn TensorFlow Keras OpenCV Hugging Face PyTorch VS Code Postman Docker Vercel Render Canva


💼 Freelance Projects

End-to-end websites I designed, built, and shipped for real wellness brands — each fully responsive, multi-page, and production-deployed.

A full-stack wellness platform built with Next.js + Tailwind CSS.

  • Rich multi-page architecture — Services, Courses, Healing, Membership, Products, Gallery
  • Booking/contact flow and a secure admin login
  • Responsive layouts with optimized images and strong on-page SEO
  • Product section and content-driven pages for 15+ health conditions

A full-stack studio website built with Next.js + Tailwind CSS.

  • Multi-page, fully responsive design with services, membership, and gallery sections
  • Product store with WhatsApp-based ordering flow
  • Membership/enquiry system with an admin dashboard for managing leads
  • Google Reviews integration and multi-location support
  • SEO-optimized and deployed to production

📜 Certifications

  • Product Analytics — Mixpanel (2026)
  • Alteryx Designer Core Certification (2026)
  • SQL (Advanced) Certification – HackerRank (2025)
  • Complete Data Science, Machine Learning, DL, NLP Bootcamp (Feb. 2025) - Udemy
  • Data Engineering Foundations Professional Certificate by Astronomer (Apr. 2025) - LinkedIn Learning
  • The Web Developer Bootcamp (Feb. 2023) - Udemy

🌐 Connect with Me

LinkedIn | GitHub | Portfolio

🚀 Always open to building impactful AI systems and full-stack products, and collaborating on real-world projects!

Pinned Loading

  1. DocSense-Privacy-First-RAG-for-Enterprise-Documents DocSense-Privacy-First-RAG-for-Enterprise-Documents Public

    A dual-mode RAG system for querying financial reports, 10-Ks, and strategy decks — runs fully offline for sensitive workloads, or cloud-deployed for demos and non-sensitive use cases.

    Python

  2. Hawkins-Distribution-Intelligence-Platform Hawkins-Distribution-Intelligence-Platform Public

    An internal IT system that gives Hawkins management a single pane of glass over distributor performance, regional demand, inventory health, service quality, and competitive positioning.

    TypeScript

  3. ShareChat-Content-Engagement-Analytics ShareChat-Content-Engagement-Analytics Public

    A complete, end-to-end product analytics system built to demonstrate the skills — SQL depth, metric design, cohort thinking, A/B test evaluation, and analytical storytelling.

    Python

  4. Mass-Attendance-AI Mass-Attendance-AI Public

    Browser-native facial recognition attendance system — enrol students via webcam, detect entire classrooms simultaneously, mark attendance in one click. Flask · SQLite · face-api.js · TensorFlow.js.…

    Python 1

  5. India-Foodgrain-Stocks-Analytics India-Foodgrain-Stocks-Analytics Public

    A comprehensive end-to-end data analytics project analyzing India's foodgrain stocks across 26 states and 177 districts from 2010-2025. The project includes data collection from India's Open Govern…

    Jupyter Notebook

  6. Citi-Credit-Analytics-Platform Citi-Credit-Analytics-Platform Public

    Production-style credit risk platform — default prediction, customer segmentation, SQL analytics & GenAI/RAG architecture proposal. FastAPI · React · scikit-learn · SQLite.

    Python