.svg)
role: Software Development Engineer (GenAI & Full-Stack)
focus:
- LLM Orchestration frameworks (LangGraph, LangChain)
- Retrieval-Augmented Generation (RAG) pipelines at production scale
- FastAPI & Node.js microservice architectures
- High-performance React / TypeScript UI systems
currently: Building autonomous multi-agent systems for enterprise SRE & knowledge workflows
ask_me_about: [GenAI system design, RAG architecture, microfrontends, 0→1 product builds]- GenAI Systems Engineer — designed and shipped multi-agent, RAG, and stateful conversational systems used in enterprise environments
- Full-Stack Architect — built Kaaryasetu, a MERN + AI platform serving 550+ active users and a 500+ member community
- Microfrontend Optimizer — improved load performance and modularity across large-scale React frontends
- Cloud & Infra — deploys and scales services on AWS EC2, with hands-on production DevOps experience
- Ask me about GenAI system design, RAG architecture, agentic workflows, or building from 0 → 1
Recall — Enterprise RAG Platform
Retrieval-Augmented Generation pipeline built for accurate, context-grounded enterprise knowledge retrieval.
| Area | Details |
|---|---|
| Core | Chunking, embedding & retrieval pipeline over enterprise knowledge sources |
| Orchestration | LangChain / LangGraph pipelines for retrieval + generation flow |
| Backend | FastAPI services exposing retrieval & Q&A endpoints |
| Goal | Reduce hallucination and ground LLM answers in verified source documents |
Sentinel — Multi-Agent SRE Copilot
A multi-agent system that assists Site Reliability Engineers with incident triage, diagnostics, and remediation guidance.
| Area | Details |
|---|---|
| Architecture | Multi-agent orchestration with LangGraph — specialized agents for detection, diagnosis & remediation |
| Backend | Python microservices for log/metric ingestion and agent coordination |
| Value | Speeds up incident response by automating first-pass root-cause analysis |
Nexa — Stateful Conversational Chatbot
A conversational AI system that maintains long-running context and state across multi-turn interactions.
| Area | Details |
|---|---|
| Core | Persistent conversation state & memory management across sessions |
| Orchestration | LangChain-based dialogue flow with tool-calling support |
| Backend | Node.js / FastAPI hybrid service layer |
Kaaryasetu — Full-Stack MERN AI Platform
Full-stack platform built end-to-end and scaled since launch in March 2025.
| Area | Details |
|---|---|
| Stack | React, Node.js, Express, MongoDB |
| Auth | Google OAuth |
| AI Features | Cold-email generator using OpenAI, Groq & LLaMA APIs |
| Infrastructure | AWS EC2 — deployed, managed & scaled |
| Community | Led a frontend bootcamp · 500+ member community |
| Impact | 550+ active users since March 2025 launch |
GenAI & LLM Orchestration
Frontend & Desktop
Backend & Databases
Cloud & DevOps
Auto-generated daily via GitHub Actions — see .github/workflows/profile-3d.yml
Open to collaborating on GenAI systems, agentic architectures, or full-stack products — reach out anytime.
.svg)