Building production AI systems

Multi-agent orchestration · Vision AI pipelines · FastAPI backends · LLM applications

• 🛠️ Maintaining MAP, SRS, and College Event System — all shipped, now in upkeep mode
• 🚀 Ex-AI/ML Intern @ Kemuri Technology — shipped COE-AI, a production vision classification service on GPT-4o mini
• 🌱 Learning LangGraph agent patterns and contributing to tortoise-orm, pydantic, rich
• 💬 Ask me about multi-agent systems, FastAPI architecture, or PR review workflows
• ⚡ Fun fact: I review every PR on my team projects myself — zero-ambiguity code review is non-negotiable

final-year AI & Data Science student. I build production-grade AI systems — not notebooks, not demos. Multi-agent orchestration, vision classification pipelines, distributed task systems, and real backends that ship and stay up.

Shipped and now maintaining MAP, a multi-agent AI automation platform with LangGraph orchestration, circuit breakers, Prometheus observability, and RBAC — led a team of four through code review across 8+ phases to completion. As an AI/ML Intern at Kemuri Technology, I shipped COE-AI, a production marine garbage classification and weight-detection service integrating GPT-4o mini vision with a live CMS pipeline.

I care about clean architecture, TDD, zero-ambiguity code review, and systems that hold up under real load.

✅ Completed — In Maintenance · LangGraph · FastAPI · Celery · PostgreSQL · Redis

Planner → Executor → Analyzer → Memory pipeline orchestrated with LangGraph stateful graphs. FAISS/Chroma RAG memory per user, ReAct executor loop with 5 real tools, confidence-scored evaluation pipeline (re-executes below 0.7 threshold), circuit breaker over all LLM calls with BentoML-served Mistral-7B fallback, RS256 JWT with RBAC, Prometheus + Grafana observability. All phases (0–4) shipped; now maintained through periodic updates.

LangGraph LangChain FastAPI Celery Redis PostgreSQL FAISS BentoML Docker React 18 TypeScript Prometheus

✅ Completed — In Maintenance · 90%+ routing accuracy · FastAPI · PostgreSQL

Confidence-based decision engine auto-resolves tickets (≥ 0.75 threshold) or escalates to human agents. TF-IDF similarity search reuses solutions from resolved ticket history. Full RBAC, bcrypt auth, layered architecture with pytest coverage. Deployed on Render + Vercel; now in maintenance with periodic fixes and updates.

FastAPI Python SQLAlchemy NLP TF-IDF JWT PostgreSQL pytest

✅ Completed — In Maintenance · Local-first · Ollama · LangGraph · Docker sandboxed execution

Agent loop with tool-calling, Docker-sandboxed code execution, FAISS memory for context retrieval. Runs fully locally on qwen2.5-coder — zero cloud dependency.

Ollama LangChain FAISS Docker FastAPI React Python

✅ Completed — In Maintenance · EfficientNet-B4 · GradCAM explainability · FastAPI · PyTorch

Production FastAPI service serving a deepfake classifier with GradCAM visual explanations per inference. React + TypeScript frontend for real-time results.

FastAPI EfficientNet-B4 GradCAM PyTorch Explainable AI React 18 TypeScript

✅ Completed — In Maintenance · 10-phase build · FastAPI · WebSocket · Celery

Full backend for clubs, events, RSVP, waitlists, QR attendance, PDF certificate generation, budgets, real-time WebSocket notifications, and admin panel. All 10 phases shipped with full test coverage; now in upkeep mode.

FastAPI PostgreSQL Redis Celery WebSocket React 18 TypeScript Neon

✅ Completed · Odoo × VIT Pune Hackathon 2026 Finalist · built in 8 hours · OCR · Multi-tenant

Multi-tenant expense system with OCR receipt scanning, multi-step approval workflows, role-based access. Built under hackathon conditions, reached national finals.

FastAPI PostgreSQL OCR React Python Multi-tenant

Python	FastAPI	React	TypeScript	JavaScript	PostgreSQL
Redis	Docker	Nginx	Git	GitHub	VS Code
Tailwind	Three.js	PyTorch	OpenCV	HTML5	CSS3
Vite	Prometheus	Grafana	Vercel	TensorFlow

AI & Agents

Backend & APIs

Frontend

Infra & Data

ML & Vision

Tooling

• Odoo × VIT Pune Hackathon 2026 Finalist — national finals, prize pool ₹45,000, built in an 8-hour sprint
• Pull Shark ×2 — PRs merged by others across team projects
• Pair Extraordinaire — co-authored commits across MAP team
• AI/ML Internship @ Kemuri Technology — shipped a production computer-vision service (GPT-4o mini + CMS integration) from design to deployment
• Sole PR reviewer across 2 shipped team platforms (MAP + College Event System) — 5-person team, all phases

Activity