Open to opportunities

Agentic AI Engineer
& Backend Architect

LLM Orchestration  ·  RAG Pipelines  ·  FastAPI Microservices  ·  Full-Stack

I'm Ramesh Das — a production-focused engineer with 6+ years building AI-first platforms, scalable backend systems, and agentic workflows. Specialized in Generative AI, multi-agent systems, LangChain, LlamaIndex, RAG pipelines, and FastAPI microservices. Currently leading AI development at KLIKY AI — shipping WinstaAI, a production agentic AI SaaS.

Agentic AI Engineer LLM Engineer Backend Architect Generative AI Developer AI Platform Engineer Nepal  ·  Remote 6+ Years

Tech Stack

Production tools across AI, backend, cloud, databases, and frontend

Agentic AI & Generative AI
LangChain LlamaIndex OpenAI GPT APIs Hugging Face Ollama DeepSeek ComfyUI Replicate Dify Langflow RAGFlow Browser-Use RunPod FAL.ai Multi-Agent Systems RAG Pipelines Tool-Calling LLMs Vector Embeddings Prompt Engineering GPU Inference Diffusion Models Speech-to-Text / TTS OCR Text-to-Image
Backend Development
Python FastAPI Django Node.js Express.js Celery Apache Kafka Debezium CDC GraphQL REST APIs WebSockets Async Programming Microservices Event-Driven Architecture JWT / OAuth 2.0 RBAC TypeScript JavaScript
Databases & Vector Stores
PostgreSQL MongoDB Redis MySQL Supabase Pinecone Weaviate Vector Search Semantic Search Embedding Pipelines
Cloud, DevOps & Infrastructure
Docker Kubernetes AWS EC2 / S3 / Lambda GCP GitHub Actions Nginx CI/CD Sentry VPS GPU Servers
Frontend
React.js Next.js TypeScript Tailwind CSS HTML5 / CSS3 SSR / SSG
Auth & Integrations
Auth0 Firebase Django Allauth Stripe PayPal Twilio DeepL Webhooks OpenAI API

Work Experience

6+ years shipping production systems across AI, full-stack, and enterprise platforms

Lead AI Full-Stack Developer
KLIKY AI
Jan 2024 – Present

WinstaAI — Agentic AI SaaS Platform

AI-driven platform combining Generative AI, agentic workflows, and multi-model LLM orchestration at production scale.

  • Architected backend with FastAPI, Django, microservices, and async task workflows
  • Built agentic AI pipelines for autonomous task execution, tool-calling, and decision-based orchestration
  • Integrated text-to-image, face swap, OCR, video/audio AI, and multi-model LLM routing
  • Developed intelligent admin: AI service management, credit systems, usage analytics, billing
  • Integrated Stripe, PayPal, RunPod, FAL.ai, and cloud deployment pipelines
Full-Stack Developer
AJATH INFO TECH
Jun 2021 – Dec 2023

Dibbly — Multilingual AI Video Translation

AI-powered speech-to-text, text-to-speech, real-time transcription, and multilingual dubbing. Generative AI services, REST APIs, and DeepL translation integration.


Paperport — AI Presentation Generator

LLM-powered tool generating structured presentations and roadmaps from text and images. Firebase auth, OTP, push notifications, and content generation workflows.

Full-Stack Developer
SARAJ SYSTEM
Dec 2019 – May 2021

Khantailor — Custom Tailoring eCommerce

Full eCommerce with custom measurements, design creation, Stripe/PayPal, Docker/Nginx, JWT/CSRF security.


PathHub — Medical Diagnostic Platform

HIPAA-focused diagnostic reporting for a large hospital network — real-time imaging, secure access, scalable reporting.


OZMED — Online Learning Platform

Subscription learning with mock exams, progress tracking, and secure content delivery.


Featured Projects

Production systems designed, built, and shipped end-to-end

WinstaAI — AI Platform

Agentic AI · Generative AI · Multi-Model SaaS

Production AI SaaS with LLM orchestration, agentic workflows, text-to-image (ComfyUI + Replicate), face swap, OCR, and video/audio AI. FastAPI microservices, async task queues, GPU inference (RunPod, FAL.ai), intelligent admin dashboard.

FastAPI LangChain ComfyUI RAG Docker Kubernetes
View Portfolio →

Dibbly — Multilingual AI Video

Speech AI · NLP · Translation Pipelines

AI-powered multilingual speech-to-text, TTS, real-time transcription, and video dubbing platform. Generative AI services, secure REST APIs, session management, DeepL translation.

Django Speech AI DeepL Firebase JWT

Paperport — AI Content Generator

LLM · Generative AI · Automation

LLM-based tool generating structured presentations and roadmaps from unstructured text and images. Full-cycle: content workflows, Firebase auth, OTP verification, push notifications.

Python OpenAI Firebase React REST API

PathHub — Medical Diagnostic Platform

Healthcare · HIPAA · Reporting Systems

HIPAA-focused diagnostic reporting platform for a large hospital network. Real-time diagnostic imaging, secure access control, scalable reporting modules, optimized healthcare workflows.

Django PostgreSQL REST API HIPAA Docker

Focus Depth

Where I spend most of my engineering time

Agentic AI Platforms
FastAPI / Python Backend
RAG Pipeline Architecture
LLM Orchestration
Generative AI Integration
Event-Driven / Kafka
Cloud & GPU Inference
Full-Stack Frontend

Open Source Templates

Enterprise-grade production starters — fullstack-open-source

FastAPI Backend

JWT Auth · RBAC · Async · PostgreSQL · Docker · Kubernetes-ready

View template →

Node.js Backend

JWT Auth · Prisma ORM · PostgreSQL · Docker · Kubernetes-ready

View template →

Django Backend

Auth · Admin Panel · DRF · PostgreSQL · Production settings

View template →

Next.js Frontend

App Router · TypeScript · Tailwind CSS · API integration

View template →

React.js Frontend

Vite · TypeScript · React Router · Modern tooling

View template →

All Projects

7+ repositories · Full-stack templates · Actively maintained

View org →

Get in Touch

Open to Agentic AI, LLM Engineer, Backend Architect, and Full-Stack roles — remote or contract