Featured
• Revamped research agent architecture, slashing API calls by 67% (from 3 to 1 per query), shrinking operational costs by 90% (to $0.003 per request), and accelerating response time by 75%.
• Designed and deployed three specialized research pipelines for distinct query categories, improving retrieval quality, response relevance, and overall research coverage across diverse user requests.
• Built a comprehensive LLM evaluation framework featuring a two-stage "LLM-as-Judge" architecture with Perplexity Sonar Pro for real-time web fact verification and GPT-5 for structured assessment of hallucination, factual accuracy, clarity, and FDA-style content quality metrics. Enabled parallel A/B testing across up to 8 model variants.
• Contributed to data analysis and model benchmarking that guided the selection of an improved AMD prediction model, achieving sub-100 ms inference latency with reliable predictive performance.
• Engineered cross-service credit deduction pipeline across three microservices using checkpoint-based aggregation and idempotent upserts, eliminating double-charge drift with balance checks refreshed within 60 seconds.
• Collaborated and Delivered 15+ production enhancements to React.js interfaces for job recommendations and worker dashboards, reducing First Contentful Paint from 1.4 seconds to 0.9 seconds and Time to Interactive from 2.4 seconds to 1.6 seconds, achieving Google Lighthouse performance score of 92/100.
• Integrated FastAPI-based AI services with frontend components to enable intelligent task matching, boosting automated assignment accuracy by 18% and reducing manual intervention overhead by 30 hours per week, in collaboration with cross-functional teams.
• Engineered cross-service credit deduction pipeline across three microservices with a 60-second cache-backed balance check, using checkpoint-based aggregation to unify 5 enrichment and 8 research credit types under one consistent ledger.
• Spearheaded development of Siamese Neural Network in PyTorch for patient verification system, achieving accuracy rate of 98.6% through rigorous testing and validation of core ML components across 5,000+ patient records.
• 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. LeetCode Rating: 1760 and CodeChef 5-star (Rating: 2040). 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
Solving algorithmic challenges and building efficient solutions
Featured
A practical framework for evaluating database paradigms, CAP/PACELC trade-offs, and real-world system architecture case studies.
A comprehensive guide to understanding and implementing Segment Trees in C++ for efficient range queries and updates.
Want to discuss a project or just chat?
Design & Developed by Shivratan Choudhary
© 2026. All rights reserved.
.jpg&w=256&q=75)
