GenAI Engineer · Backend Architect · LLM Systems

Building AI
that ships to
prod.

Hey, I'm Priyanshu Patel — I work at the intersection of LLMs, backend infra, and cloud deployment. Not just prompts. The whole system.

RAGLangChain FastAPIAWS Node.jsReact.js
Profile
AVAILABLE
01

What I Build

[01]
🧠
LLM Systems & RAG

Production-grade RAG pipelines, vector search, embedding strategies, and LLM orchestration that go beyond demos into real deployments.

LangChainQdrantOpenAIGemini
[02]
⚙️
Backend Architecture

Scalable APIs, microservices, async queues, and database design built to handle production loads with observability baked in.

FastAPINodeJSPostgreSQLRedis
[03]
☁️
Cloud & DevOps

CI/CD pipelines, containerized deployments, and cloud-native infra that keep AI products running reliably at scale.

AWSDockerGitHub ActionsNginx
[04]
🤖
Agentic Workflows

Multi-agent systems, autonomous task orchestration, tool use, memory architectures, and LLM eval frameworks.

AgentsTool UseEvalsObservability
[05]
🗄️
Data Engineering

ETL pipelines, vector databases, hybrid search, and data prep workflows that feed production AI systems reliably.

MongoDBQdrantHuggingFaceETL
[06]
🖥️
Full-Stack Interfaces

React and Next.js frontends that surface AI capabilities in clean, usable interfaces — because UX matters for adoption.

ReactNext.jsTailwindTypeScript
02

About Me

// background.md

I'm a GenAI + backend engineer obsessed with taking AI from Jupyter notebooks into real production systems. I believe the model is 10% of the product — the infra, pipelines, observability, and deployment are everything else.

I've built RAG pipelines serving real users, agentic workflows that orchestrate multi-step tasks autonomously, and backend APIs that scale under load.

"The model is 10% of the product. The infra around it is everything."
LLM/GenAI
95%
Backend
90%
Cloud/DevOps
82%
Frontend
72%
Data Eng.
78%
// stats.json
10+
AI Projects Shipped
5+
Production APIs
Lines of Inference
// currently_working_on.ts
Agentic workflows & multi-agent orchestration
LLM evals & production observability
Retrieval-augmented generation at scale
Open-source AI tooling contributions
03

Selected Projects

GenAI · RAG System
YouTube Q&A Engine

Built a full-stack Chrome Extension enabling semantic Q&A over YouTube videos using a RAG pipeline. Integrated transcript ingestion, vector search, and LLM-based answer generation with timestamp grounding.

FastAPI LangChain Qdrant Gemini
View project →
Full Stack · Production
Wellness Platform

Production-ready platform for discovering wellness centers, booking experts, and tracking health activities. Built with scalable backend architecture, OAuth authentication, and optimized PostgreSQL queries.

React Node.js PostgreSQL AWS
View project →
AI · Voice Agents
Matrimonial Voice Agent

Real-time AI voice agent for matrimonial platforms using Sarvam STT/TTS with structured intent extraction. Designed low-latency conversational pipeline with WebSockets, caching, and decision engine.

FastAPI GPT-4o-mini Redis PostgreSQL
View project →
Full Stack · In Progress
CGS — Common Ground Solutions

India's green infrastructure and carbon credit lifecycle platform. Multi-portal SPA architecture serving project developers, corporate ESG teams, and FPOs — covering credit issuance, retirement workflows, BRSR/GRI/CDP report generation, and marketplace.

React NestJS PostgreSQL TypeScript Kafka AWS
View project →
04

Experience Timeline

Nov 2025 — Jan 2026
Full Stack Developer Intern
// Cufront Healthcare
  • Built production-ready frontend features using React and collaborated closely with backend teams
  • Implemented optimized search with filters and debouncing, improving API efficiency and UX
  • Worked with REST APIs, data fetching strategies (React Query), and basic backend integrations
06

Writing & Thoughts

RAG · Engineering
Why Your RAG Pipeline Fails in Production (And How to Fix It)

Chunking strategies, re-ranking, hybrid search, and the retrieval failures nobody talks about until they hit 10k users.

Mar 20258 min read
LLM · Systems
The Model is 10% — Building the Other 90%

A deep-dive into the infra, observability, and reliability patterns that turn LLM experiments into production systems.

Feb 202512 min read
Agents · Architecture
Designing Multi-Agent Systems That Actually Work

Planner-executor-critic patterns, tool reliability, memory persistence, and avoiding the failure modes of naive agentic loops.

Jan 202510 min read