Skip to content
View agarwalsoham993's full-sized avatar

Block or report agarwalsoham993

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
agarwalsoham993/README.md

Hi there, I'm Soham Agarwal πŸ‘‹

🎯 About Me

I'm a full-stack developer and AI/ML enthusiast passionate about building production-ready systems that solve real problems. I specialize in:

  • Machine Learning & AI: practical models, embeddings, and RAG pipelines
  • Backend Systems: scalable APIs, microservices, and deployment infrastructure
  • Quantum Computing: quantum algorithms, optimization research, and prototypes
  • Computer Vision & Game AI: visual systems and intelligent agents

I focus on reproducible demos, clean APIs, and deployable prototypes at the intersection of research and product.


πŸ› οΈ Tech Stack

Python Go JavaScript TypeScript FastAPI Docker PyTorch TensorFlow AWS


🀝 Connect With Me

GitHub LinkedIn Medium YouTube Website


Continuously building and learning | Profile Views

Soham Agarwal Profile

Soham Agarwal

πŸš€ Full-stack developer β€’ AI/ML enthusiast

πŸŽ“ IIT Kharagpur


πŸ“Š GitHub Stats




🎯 Highlighted Projects

1. Code-Execution-Engine β€” Secure, Scalable Code Runner

image

2. OpenBALC β€” Open source courses management and AI learning platform.

image

3. CalendarSYNC β€”

  • Repo: https://github.com/Threnlabs/CalendarSYNC
  • Tech: Python, FastAPI, LLMs
  • Description: Intelligent Scheduling - Automatically find the best times for classes and meetings, ensuring a conflict-free schedule.
image

4. GNN-QC β€” Graph Neural Networks Γ— Quantitative Finance

  • Repo: https://github.com/agarwalsoham993/GNN-QC
  • Tech: PyTorch, Quantum Computing
  • Description: Exploratory research notebooks combining graph neural networks with small quantum circuits for hybrid quantum-classical prototyping.
image

5. WhatsApp-RAG-Example β€” RAG Chatbot on WhatsApp


πŸš€ Key Focus Areas

Embeddings & Retrieval Systems

  • Open-source and cloud-hosted embedding models
  • Vector store integration (FAISS, Milvus, Pinecone)
  • Production-ready RAG pipelines for LLM applications

Quantum Algorithms & Optimization

  • Quantum circuit design and simulation
  • Hybrid quantum-classical algorithms
  • Optimization research with quantum-inspired methods

Scalable Backend Systems

  • Microservices architecture with FastAPI
  • Container orchestration and deployment
  • High-performance inference servers

MLOps & AI Orchestration

  • Agentic workflows and LLM orchestration (LangChain, AutoGen)
  • End-to-end model lifecycle management (MLflow, W&B)
  • Data pipeline automation and model deployment

πŸ“š Current Work

I'm actively working on:

  • Advanced RAG systems and LLM tooling for production environments
  • Quantum algorithms for combinatorial optimization
  • Scalable backend infrastructure and distributed systems
  • Research prototypes that bridge theory and practical application

🀝 Connect With Me

GitHub LinkedIn Medium YouTube ![website](https://globe.img


Pinned Loading

  1. Code-Execution-engine Code-Execution-engine Public

    A scalable, self-contained Code Execution Engine written in Go. Its core function is to execute user-submitted code in secure, isolated Docker containers and return the results via a simple REST API.

    Go 2

  2. Neural-Networks Neural-Networks Public

    Implementation and building of Neural Network from scratch in C++, with both forward and Backward Propagation.

    C++

  3. RAG RAG Public

    Retrieval Augmented Generation

    Python

  4. Docker Docker Public

    Python

  5. Market-basket-Analysis Market-basket-Analysis Public

    Implementing NLP and Machine Learning for real life problem faced in Shelf products placement in supermarket and purchase prediction.

  6. Unbeatable-tictactoe Unbeatable-tictactoe Public

    unbeatable tic tac toe game , using C++

    C++