Vaibhav Dwivedi designs and ships complete products — web platforms, AI systems, and real-time applications.
Full-Stack Web Development
End-to-end web applications with React and Next.js frontends, Node.js APIs, PostgreSQL or MongoDB data layers, authentication, and production deployment on Docker and AWS.
AI & Generative AI Development
Production GenAI applications using LLMs and Python — including document intelligence systems, prompt evaluation, and model integration for real business workflows.
RAG Applications
Retrieval-Augmented Generation pipelines with LangChain and vector search — document-grounded chatbots, embedding tuning, and chunking strategies for accurate, low-latency responses.
Real-Time Applications
Real-time platforms using WebRTC, Socket.IO, and Redis Pub/Sub — anonymous chat, live presence, voice/video, and architectures tested for 150+ concurrent users.
SaaS & Product Development
Complete product builds from architecture through CI/CD — admin dashboards, lead capture, inventory systems, and client-facing platforms such as AuraHonda and Baansinfra.
Full Stack Developer
- Developing and optimizing full-stack web applications using React, Node.js, and REST APIs; collaborating in an agile, industry-oriented environment to ship features across the complete development lifecycle.
- Implementing scalable backend logic, responsive UI components, and streamlined CI/CD workflows for real-world client-facing products; contributing to code reviews and architectural decisions.
React
Node.js
Git
GitHub
DockerBackend Developer
- Building UniTalks — an anonymous real-time chat platform with voice/video via WebRTC, designed to scale to 1,000+ concurrent connections.
- Owned backend architecture around Node.js, Socket.IO, and Redis Pub/Sub for distributed session state; containerized services with Docker and deployed behind Nginx on AWS EC2.
- Set up GitHub Actions CI/CD to cut deployment time by ~75%; load-tested the stack at 150+ concurrent users to validate performance under real traffic.
Node.jsReactDocker
AWS
NginxGitGenerative AI Intern
- Built production GenAI applications using LLMs, LangChain, and Python; delivered 8 RAG pipelines for document intelligence with vector search and tool-augmented agents.
- Reduced inference latency by 40% via chunking and embedding tuning; evaluated 5+ prompt strategies, boosting RAG faithfulness scores by 22% on internal benchmarks.
PythonGitDockerEnd-to-end ownership
From architecture to CI/CD, I've owned products end to end — not just tickets in a sprint.
Your turn
Got something similar in mind — a platform, dashboard, or product launch? I'd like to hear what you're building.
Published Patent
System and Method for Stress and Pain Detection Using Multi-Scale Transformer-Based Neural Networks — Application No. 202641065281
RAG Chatbot
Document-grounded Retrieval-Augmented Generation pipelines with LangChain, vector search, and LLMs — including production RAG work that cut inference latency by ~40%.
Ongoing Project — ResearchPilot
AI-powered research intelligence platform combining fine-tuned LLMs, Retrieval-Augmented Generation (RAG), semantic search, and machine learning for paper analysis, abstract enhancement, statistical recommendations, and research gap discovery.
GenAI & ML
LLMs, vector search, RAG, and production AI workflows — from prototype to deployment.
Have an idea worth building?
Whether it's a startup MVP, an internal tool, or an AI product — tell me what you're working on.
Contact Form
Please contact me directly at dwivedivaibhav3110(at)gmail.com or drop your info here.