Welcome to the Page of
Janmajay Kumar
MLOps, Physicist
Professional Skills
My Skills
Experienced in data analysis, probability theory, and statistical modeling. Familiar with hypothesis testing, regression analysis, and data visualization to extract insights from data.
Proficient in Python with strengths in computational algorithms, object-oriented programming, and functional paradigms. And developing robust, efficient solutions for complex data analysis and scientific computing challenges.
Proficient in c++ / OOP framework. Hands on experience in leveraging c++ based software framework like GEANT4
Developed a deep learning model that achieved 95% accuracy in particle classification tasks. Experienced in developing end-to-end ML pipelines, including data preprocessing, feature engineering, and hyperparameter tuning.
I have hands-on experience in Monte Carlo simulations, using statistical techniques to model complex systems and analyze probabilistic outcomes.
Proficinet in cloud technology, with hands-on experience in deploying and managing cloud-based solutions using Google Cloud, and Azure. on google cloud. BigQuery and VetexAi cloud function are my favorite.
Portfolio
My Projects
Neutron Capture and Cerenkov Simulation
This project simulates neutron capture using Geant4 for LEGEND-1000 experiments. It models neutron interactions with different materials and analyzes the results using ROOT. This work was part of my research assistant role at the University of Tübingen.
Full Stack Web App
A dynamic website a prototype jos advertisement website
Data-Engineering: Weather and Flight Data Project
This project is part of the training at WBS Coding School. The goal of this project is to develop a data engineering pipeline that fetches weather data and flight information using external APIs, stores the data in a MySQL database, and provides functionality for retrieving and analyzing the data
ETL Pipeline on Google Cloud
This project is part of the training at WBS Coding School. This project demonstrates how to build an ETL (Extract, Transform, Load) pipeline on Google Cloud using Cloud Functions, BigQuery, and Cloud Scheduler.
Graph-Powered Retrieval-Augmented Generation (RAG) for Smarter Recommendations
This project is part of the training at WBS Coding School. This project demonstrates the integration of Retrieval-Augmented Generation (RAG) with graph databases (Neo4j) and Large Language Models (LLMs) to create an intelligent and scalable recommendation system.
MyPage
Created Portfolio , HTML, CSS, JavaScript.
Physics Informed Machine Learning
Physics-Informed Neural Networks (PINNs) are a powerful scientific machine-learning technique used to solve problems involving Partial Differential Equations (PDEs).
Cherenkov Gamma Telescope Event Classification
This repository contains code for training machine learning models to classify events detected by a ground-based atmospheric Cherenkov gamma telescope. The goal is to discriminate between gamma ray signals and background noise caused by cosmic ray showers based on the characteristics of the shower images captured by the telescope..
Higgs Boson Machine Learning Challenge(Kaggle)
Kaggle's Higgs Boson Machine Learning Challenge, applying data science to predict particle collisions at the Large Hadron Collider
Computational Astrophysics M.Sc coursework
This is part of the Computational Astrophysics course during my Master's at the University of Tübingen
N-Body Problem
As part of my Master's in Astro and Particle Physics at the University of Tübingen, I implemented N-Body simulations to study the dynamics of celestial bodies.