← 返回首页
vpmistry13 (Vishal Mistry) · GitHub
Skip to content

Navigation Menu

Toggle navigation
Sign in
Appearance settings
Search or jump to...

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted
Cancel Submit feedback

Saved searches

Use saved searches to filter your results more quickly

Cancel Create saved search
Appearance settings
Resetting focus
Overview Repositories 10
  • Ahmedabad, Gujarat, India
Block or report user

Block or report vpmistry13

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.

Add an optional note
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Block user
Report abuse

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

Report abuse
vpmistry13/README.md

Hi, I'm Vishalkumar Mistry 👋

Senior Full Stack Engineer · React · Next.js · NestJS · Generative AI · LLM Apps · Prompt Engineering

Based in Ahmedabad, India · 10+ years building enterprise-grade applications

🚀 What I Do

I build full stack applications at the intersection of modern web engineering and Generative AI. During the day I lead frontend modernisation at LT, rewriting legacy enterprise systems into scalable React and Next.js applications. In my own time I architect AI-integrated SaaS products from scratch.

I am especially interested in multi-model LLM orchestration, IMG2IMG AI pipelines, and building real products that use Generative AI practically — not just as a demo.

🛠️ Tech Stack

Frontend

Backend & Infrastructure

Generative AI & LLMs

Payments

🤖 What I'm Building

AI Product Photography Platform

Upload one product photo → get 10 professional studio-quality images in under 3 minutes

  • Hybrid AI pipeline: Gemini 3 Pro Image for hero shots + Replicate FLUX.1 Kontext for batch angle generation
  • Dynamic angle selection: Gemini Vision analyses each product and recommends the best angles based on garment type, silhouette, and user's photo count setting
  • 61% cost reduction achieved through provider-agnostic architecture — from $0.67 to $0.26 per 10-angle job
  • LoRA fine-tuning pipeline planned on FLUX.1 Kontext Dev via Replicate for category-specific photoshoot style training
  • Stack: React Native (Expo) · NestJS 11 · PostgreSQL · Redis · BullMQ · AWS S3 + CloudFront · Razorpay · Stripe

🧠 AI & LLM Experience

Models worked with: ├── Google Gemini 3 Pro Image → Hero product shot generation (IMG2IMG) ├── Google Gemini 3.1 Flash Image → High-volume angle generation ├── Google Gemini 2.5 Flash → Vision validation + structured JSON extraction ├── OpenAI gpt-image-2 → Image generation (low/medium/high quality) ├── Replicate FLUX.1 Kontext Dev/Pro → IMG2IMG product photography + LoRA fine-tuning └── Microsoft Copilot → Agentic AI application development Techniques: ├── Prompt engineering (image-led, category-specific, minimal token prompts) ├── Gemini thinkingConfig multi-image loop (single-call batch generation) ├── Dynamic LLM-based angle selection via vision reasoning ├── Hybrid multi-provider orchestration with provider-agnostic service architecture ├── Token economics and AI cost modelling ($/image optimisation) └── LoRA fine-tuning pipeline design for custom model training

🎓 Certifications

  • 🏆 AZ-900 Microsoft Certified Azure Fundamentals — Microsoft
  • 🤖 Agentic AI and AI Agents: A Primer for Leaders — Vanderbilt University
  • 🧠 Generative AI: Working with Large Language Models — LinkedIn Learning
  • 💬 Prompt Engineering for ChatGPT — Coursera
  • ⚛️ React Certified — Triplebyte
  • 🏢 iLead Program — LTM

🔧 Code Assistant Tools I Use Daily

Tool Use case
Claude CLI Architecture decisions, complex prompt engineering, code review
OpenAI Codex Code generation and refactoring
Google AI Studio (Antigravity) Gemini API testing, multi-image generation research
Factory.ai Agentic development workflows

📫 Let's Connect

"I don't just use AI tools — I build the infrastructure that runs them."

@vpmistry13's activity is private

Footer

© 2026 GitHub, Inc.