Skip to content
View idesmukh's full-sized avatar
26 followers · 303 following

Block or report idesmukh

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 supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
idesmukh/README.md

Hi there!

I'm Muhammad Ibad Desmukh, a Software Engineer and Open Source Contributor holding an MSc Computing and Information Systems degree with Distinction. I am skilled in machine learning and cloud platforms, with a focus on MLOps and scalable AI infrastructure.

What I Work With

  • Programming Languages: C, Python, SQL
  • AI and Machine Learning: PyTorch, scikit-learn, pandas, NumPy
  • DevOps and MLOps: Amazon Web Services (AWS), Docker, FastAPI, Linux, Git, Bash, AWK, pytest
  • Databases: Oracle Object-Relational Database Management System (ORDBMS)

Featured Projects

Fault-Tolerant ML Training System (Solar Power Forecasting)

  • Engineered a production-ready machine learning training system with atomic write checkpointing for fault-tolerant LSTM solar power forecasting.
  • Implemented automatic state recovery, preserving model and optimizer states for cost-effective training on Amazon Web Services (AWS).
  • Technologies: PyTorch, pytest, Docker, FastAPI, AWS

Linux Server Monitoring Tool

  • Created a Linux-based server monitoring tool for parsing system metrics.
  • Provides real-time visibility into CPU, memory, and disk utilization.
  • Technologies: Bash, AWK, Linux

Intelligent, low-cost agricultural field monitoring system

  • Architected an agricultural monitoring system using C language, ESP32 microcontrollers, Bluetooth and Wi-Fi.
  • Achieved a low cost of GBP 56, real-time distributed sensor data collection, cloud integration through Google Sheets API, and automated environmental monitoring.
  • Technologies: C language, ESP32 microcontrollers, Bluetooth, Wi-Fi

Corporate financial risk level prediction

  • Developed a prediction model with scikit-learn, pandas and NumPy using Decision Tree and K-Nearest Neighbours classification.
  • Achieved 87% test accuracy through recursive feature elimination on a financial ratios dataset.
  • Implemented a cross-validation and data preprocessing pipeline.
  • Technologies: scikit-learn, pandas, NumPy

Database for a college library system

  • Designed and implemented a relational database for a college library system using Oracle Object-Relational Database Management System.
  • Developed SQL scripts for table creation, data population, view definitions and complex queries to manage resources, members, loans and reservations.
  • Technologies: Oracle Object-Relational Database Management System, SQL

Pinned Loading

  1. fault-tolerant-ml-training fault-tolerant-ml-training Public

    Fault-tolerant machine learning training pipeline for solar power forecasting

    Python

  2. systemeye systemeye Public

    Bash script to analyze server performance statistics on Ubuntu systems

    Shell

  3. pytorch pytorch Public

    Forked from pytorch/pytorch

    Tensors and Dynamic neural networks in Python with strong GPU acceleration

    Python

  4. cuda-performance-engineering cuda-performance-engineering Public