Skip to content
View shubhro2002's full-sized avatar
🤯
Going Insane
🤯
Going Insane
3 followers · 5 following

Block or report shubhro2002

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
shubhro2002/README.md
Profile Banner Typing Animation

AI Systems Engineer / Machine Learning Engineer

Exploring Retrieval-Augmented Generation (RAG) pipelines, query transformation, and data privacy.

LinkedIn Portfolio

About Me

I am a systems designer focused on the intersection of generative AI, scalable architecture, and data security. My work revolves around making large language models more accurate, efficient, and safe for enterprise environments.

  • 🔭 Currently focusing on: Advanced RAG pipeline architecture and context-aware query transformation.
  • 🌱 Researching: Enterprise data privacy guardrails and compliance within LLM workflows.
  • 💬 Ask me about: Vector databases, embedding optimization, and integrating foundational models.
  • 📫 How to reach me: shubhrajyoti.dhar@outlook.com

🛠️ Tech Stack & Tools

AI, LLMs & Data Science

Python PyTorch LangChain Hugging Face OpenAI

Vector Databases & Storage

MongoDB MySQL FAISS

Architecture & Tools

FastAPI Docker Linux

Featured Projects

  • Agentic Podcast Studio: A multi-agent system leveraging hierarchical retrieval to synthesize complex research papers into audio-ready formats.
  • Corrective RAG (CRAG) System: An enterprise-grade Retrieval-Augmented Generation pipeline built for secure corporate data querying under strict hardware constraints.
  • VAE Anomaly Detection Engine: A TensorFlow-based Variational Autoencoder (VAE) designed for robust anomaly detection.
contribution snake

footer

Pinned Loading

  1. Agentic-Podcast-Studio Agentic-Podcast-Studio Public

    This project takes a folder of PDF research papers and transforms them into a studio-quality, multi-speaker podcast. It uses a LangGraph Agentic Swarm to draft and self-correct the script, LlamaInd…

    Python

  2. Corrective-RAG Corrective-RAG Public

    A self-correcting Agentic RAG pipeline with MongoDB Vector Search, built to run entirely on constrained local hardware.

    Python 1

  3. Unsupervised-Anomaly-Detection-in-Suspicious-Web-Traffic-Using-Autoencoders Unsupervised-Anomaly-Detection-in-Suspicious-Web-Traffic-Using-Autoencoders Public

    This project focuses on building an autoencoder-based anomaly detection model to learn latent patterns in malicious web traffic. The dataset provided contains only attack traffic, with no examples …

    Jupyter Notebook 1

  4. demand-intelligence-system demand-intelligence-system Public

    An end-to-end production-style machine learning system for forecasting retail demand using dynamic feature engineering, asynchronous external data integration, and real-time inference.

    Jupyter Notebook

  5. Dynamic-Pricing-Causal-Engine Dynamic-Pricing-Causal-Engine Public

    An enterprise-grade Causal Inference API for dynamic pricing, featuring Double Machine Learning and k-Anonymity privacy architectures.

    Python 2

  6. YouTube-Comment-Sentiment-Emotion-Topic-Analysis YouTube-Comment-Sentiment-Emotion-Topic-Analysis Public

    This project analyzes YouTube comments to extract insights about audience sentiment, emotions, sarcasm, and discussion topics. The pipeline combines text preprocessing, sentiment analysis, sarcasm …

    Jupyter Notebook