Featured
• Delivered 15+ production enhancements to React.js interfaces, optimizing First Contentful Paint from 1.4s to 0.9s and Time to Interactive from 2.4s to 1.6s, achieving Google Lighthouse score of 92/100.
• Integrated FastAPI-based AI services for intelligent task matching, boosting automated assignment accuracy by 18% and reducing manual intervention by 30 hours/week.
• Implemented internationalization support for 5 Indian languages (Hindi, Bengali, Tamil, Telugu, Marathi), increasing engagement by 25%.
Dec 2024 - Feb 2025
Nagaur, India
• Spearheaded development of Siamese Neural Network in PyTorch for patient verification, achieving 98.6% accuracy across 5,000+ patient records.
• Built and validated biometric data verification pipeline using PyTorch and FastAPI, cutting manual verification errors by 18% and improving data integrity.
• Engineered backend services with Node.js and Express.js, designing hospital system integration architecture that enabled 400+ daily patient transactions while maintaining 99.5% system uptime.
Featured
Built scalable banking exam platform with real-time analytics, achieving low-latency performance under peak traffic. Deployed on Vercel with Neon PostgreSQL and password-based authentication, increasing login success rate by 40%. Integrated Gemini AI to auto-generate 100+ questions and flashcards, reducing content creation effort by 3× and improving study efficiency by 35%.
Developed browser-based style transfer application using TensorFlow.js with 4 pre-trained models (56MB total). Optimized dual-style blending with warm-up strategies, reducing initial inference time from 3.2s to 850ms (73% improvement) and increasing user interaction by 30%.
Implemented Neural Style Transfer system in PyTorch using pre-trained VGG-19 with optimized content-style loss functions. Processed 100+ image pairs with 95% positive feedback, improving generation quality by 40% and achieving 30-second render time at 1024×1024 resolution.
Engineered high-performance matrix multiplication combining DeepMind's Algorithm and Winograd's Method, achieving 50% faster processing than standard implementations. Implemented Strassen-Winograd as base case, reducing computation time for 1000×1000 matrices from 3289ms to 791ms (76% improvement). Scaled to 4096×4096 matrices with sub-second latency without hardware acceleration.
About
Competitive programmer and backend engineer with a passion for building scalable, high-performance systems. Codeforces Candidate Master (Rating: 1913). Specialized in optimizing backend architectures, database performance, and algorithmic efficiency. Expertise in C++, Node.js, FastAPI, and PostgreSQL optimization.
Skills
shivbera18's GitHub & LeetCode journey over the past year
Fetching your coding activity data
Active on multiple competitive programming platforms
Featured
A comprehensive guide to understanding and implementing Segment Trees in C++ for efficient range queries and updates.
Learn how to deploy PyTorch models in production using FastAPI for high-performance, scalable machine learning APIs
Want to discuss a project or just chat?
Design & Developed by Shivratan Choudhary
© 2025. All rights reserved.
.jpg&w=256&q=75)
