Skip to content
View hitesh-bhatnagar's full-sized avatar
🎯
Looking for exciting projects to work on.
🎯
Looking for exciting projects to work on.

Block or report hitesh-bhatnagar

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
hitesh-bhatnagar/README.md

Typing SVG


⚡ About Me

💡 I don't just use AI frameworks — I build the engines that run them.

I'm an Electronics & Communication Engineer at VIT Vellore, bridging the gap between low-level systems programming and cutting-edge Deep Learning. My work spans from writing bare-metal C for RTOS schedulers to building C++ LLM inference engines and publishing ML research in peer-reviewed journals.

  • 🔬 Research Intern @ IIT Goa — Hybrid Deep Learning ANC model (MSE: 2.9e⁻⁵, SNR: 27.10 dB)
  • 📄 Published in Elsevier DSP Journal (2026) — Logistic Distance Metric Adaptive Filter for ANC
  • 🛡️ IT Risk & AI Intern @ Aumyaa Consulting — ITGC Audits for ONGC & BMW Financial Services
  • 🚀 Current Focus: LLM Inference Optimization · Real-time Signal Processing · Embedded Kernels

🏆 Highlights

📰 Publications

[Elsevier – Digital Signal Processing, 2026] Design of Logistic Distance Metric Based Robust Adaptive Filter for Active Noise Control

[IEEE – ICAAIC 2025] A Novel Three-Layer Hybrid Cryptographic Framework using Enhanced Classical Ciphers

[ANRF-Sponsored NEleX 2026 – Provisionally Accepted] Graph-Based Zero-Day IoT Botnet Detection


🛠️ Featured Projects

C++ Docker LLM

Containerized local LLM inference engine built from scratch in C++:

  • 4-bit quantized (GGUF) model support with custom Top-K/Temperature sampling
  • Full RAG pipeline: document retrieval + prompt augmentation
  • Agentic File I/O tools + Docker deployment for reproducible builds

C Linux

Full RTOS simulator in C implementing OS internals:

  • Priority-based scheduler with context switching & task states
  • IPC mechanisms: semaphores, interrupt simulation
  • CLI-based runtime task control and debugging interface

C DBMS

Lightweight in-memory DB engine with REPL-based SQL-like interface:

  • Insert, select, update, delete with command parsing
  • Binary search-based lookup for efficient ID-based retrieval
  • Sorted record insertion — built from DBMS internals first principles

Python Jupyter

Sentiment-driven crypto market analysis pipeline combining NLP and trading signals for data-driven decision support.


🧰 Tech Stack

Languages

AI / ML / DL

Systems & Hardware

Cloud & Tools


GitHub Stats

Contribution Graph


🤝 Let's Connect

   

🎯 Open to Research Collaborations · ML/Systems Roles · Team Projects · Hackathons/Contests

Pinned Loading

  1. Crypto-Sentiment-Trading-Analysis Crypto-Sentiment-Trading-Analysis Public

    Jupyter Notebook 1

  2. Embedded-RTOS-Simulator-C-Learning-Project Embedded-RTOS-Simulator-C-Learning-Project Public

    A Learning Project for Real-Time OS Concepts, Task Scheduling, and Embedded Systems

    C 1

  3. Embedded_Systems Embedded_Systems Public

    Github repo that documents each stage of my journey to learn Embedded systems

    C 1

  4. Expense-Tracker_App_with_ML Expense-Tracker_App_with_ML Public

    Python 1

  5. Telco-Customer-Churn-Predictor-Full-Stack-ML-App- Telco-Customer-Churn-Predictor-Full-Stack-ML-App- Public

    Tech Used: Python, Scikit-Learn, LightGBM, FastAPI, Streamlit, SHAP

    Jupyter Notebook 1

  6. Nano-RAG-CPP Nano-RAG-CPP Public

    A high performance, containerized Local LLM Inference Engine build in C++. Features a custom RAG system, Agentic File I/O tools, and Docker deployment.

    C++ 2