Open to opportunities

Agentic AI Engineer
& Backend Architect

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

I'm Ramesh Das. I've spent 6+ years writing software that has to survive real traffic, not just demos. Most days I'm deep in Generative AI work — multi-agent systems, RAG pipelines, LangChain, LlamaIndex — and the FastAPI microservices that keep those features stable. I lead AI engineering at KLIKY AI on WinstaAI, our live agentic AI SaaS.

Agentic AI Engineer LLM Engineer Backend Architect Generative AI Developer AI Platform Engineer Nepal  ·  Remote 6+ Years
Portrait of Ramesh Das — Agentic AI Engineer and Backend Architect

Tech Stack

What I reach for when building AI features, APIs, data stores, and product UI

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

Teams and products where I owned the build from early design through release

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

WinstaAI — Agentic AI SaaS Platform

WinstaAI is our customer-facing SaaS. It picks models on the fly, runs agent workflows, and serves generative tools people use in their normal workday.

  • Split the backend across FastAPI, Django, microservices, and async workers so heavy AI jobs never freeze the API
  • Wrote agentic AI pipelines that call tools, decide next steps, and finish multi-step tasks on their own
  • Hooked up text-to-image, face swap, OCR, video and audio models, and routing across several LLM providers
  • Shipped an admin area for service toggles, credits, usage numbers, and billing
  • Tied in Stripe, PayPal, RunPod, and FAL.ai, then pushed releases through our cloud deploy flow
Full-Stack Developer
AJATH INFO TECH
Jun 2021 – Dec 2023

Dibbly — Multilingual AI Video Translation

Owned the speech side: speech-to-text, text-to-speech, live captions, and dubbing across languages. REST APIs carried the Generative AI work, with DeepL handling translation.

Paperport — AI Presentation Generator

Built an LLM flow that turns rough text and images into decks and roadmaps. Firebase handled login, OTP, and push alerts around the generation pipeline.

Full-Stack Developer
SARAJ SYSTEM
Dec 2019 – May 2021

Khantailor — Custom Tailoring eCommerce

Full shop for custom clothing: measurements, design tools, Stripe and PayPal checkout, Docker and Nginx hosting, JWT and CSRF on the sensitive routes.

PathHub — Medical Diagnostic Platform

Helped build a HIPAA-focused reporting stack for a large hospital network. Imaging views, tight access rules, and reports that wouldn't fall over as volume grew.

OZMED — Online Learning Platform

Subscription courses with practice exams, progress tracking, and locked-down content delivery.

Featured Projects

Selected work I've designed, coded, and released

WinstaAI — AI Platform

Agentic AI · Generative AI · Multi-Model SaaS

Live SaaS for agent workflows and multi-model jobs: text-to-image via ComfyUI and Replicate, face swap, OCR, and media AI. FastAPI services, async queues, GPU time on RunPod and FAL.ai, plus an ops admin console.

FastAPI LangChain ComfyUI RAG Docker Kubernetes
View Portfolio →

Dibbly — Multilingual AI Video

Speech AI · NLP · Translation Pipelines

Speech and video product covering multilingual STT, TTS, live transcription, and dubbing. Generative AI sits behind authenticated REST APIs, sessions, and DeepL.

Django Speech AI DeepL Firebase JWT

Paperport — AI Content Generator

LLM · Generative AI · Automation

Takes messy notes and images and turns them into structured presentations and roadmaps. Generation pipeline plus Firebase auth, OTP, and push notifications.

Python OpenAI Firebase React REST API

PathHub — Medical Diagnostic Platform

Healthcare · HIPAA · Reporting Systems

Hospital diagnostic reporting with HIPAA-minded access control, imaging support, and reporting modules built to handle growing volume without sloppy data handling.

Django PostgreSQL REST API HIPAA Docker

Focus Depth

How I actually spend my engineering week

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

Starters I keep current in 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

Remote or contract — agentic AI, LLM work, backend architecture, or full-stack builds

✉
mrdasdeveloper@gmail.com Email
💬
+977 9700864900 WhatsApp
⌥
github.com/mrdasdeveloper GitHub
⬡
www.rameshdas.dev Portfolio
↓
Download Resume PDF Resume
★
fullstack-open-source GitHub Organization · 7+ repos
🔥 50% Exclusive Discount

Work with me directly.

Skip the agency layer. You get a senior full-stack and agentic AI engineer, fixed rates, and code meant for production.

Hourly Consulting
Market Standard: $60 - $80
$25–29-50% Off
Pay-as-you-go · Billed weekly
  • AI engineering: $29/hr
  • Full-Stack dev: $25/hr
  • Backend engineering: $29/hr
  • Business automation: $25/hr
  • Flexible schedule, async friendly
🚀 Book Hourly Work
Best Value
Monthly Retainer
Market Standard: $4,000+
$1,899–1,999/ month
160 hrs · Full-time equivalent
  • Dedicated full-time capacity
  • Focus on AI, Backend, or Full-Stack
  • Daily standups + weekly reports
  • Direct Slack/WhatsApp comms
  • Invoiced monthly (NET-7)
  • Cancel anytime with 2-week notice
🚀 Discuss Retainer
Fixed-Price Project
Market Standard: Market Value
CustomQuote
Milestone-based · Clear scope
  • Automation project: from $799
  • Backend API project: from $1,199
  • SaaS MVP: from $1,899
  • AI agent / RAG: from $1,999
  • Invoiced at completed milestones
🚀 Request Quote

💡 Direct clients only: These prices are for hiring me straight — no agency cut. They already include my current 50% discount.

Service Profiles

All service pages AI Automation Engineer Best Custom Website Developer Chatbot Developer Hire Full Stack Developer Hire Node.js Developer Hire Python Developer Hire Remote Software Engineer Hire SaaS Developer Software Developer to Hire Website Developer

Custom Web Development Guides

Hiring a web dev company Post-launch support Full-stack development Project timelines Pricing models E-commerce builds Security features Third-party integrations Maintenance packages Who needs custom web dev Mobile optimization CMS integration Client involvement SEO-friendly builds Scalable architecture Contract questions Prototype & demo Feature updates UX design Project deliverables

Global Tech Hiring Hubs

Hire Developers USA Hire Developers Canada Hire Developers UK AI Engineer San Francisco FastAPI Developer NYC Hire Developers Middle East Hire Developers Saudi Arabia AI Engineer Dubai FastAPI Developer Riyadh Hire Developers Singapore Hire Developers Australia Hire Developers Germany Hire Developers Japan Backend Architect Berlin

Expertise & Hire Me For

Hire Agentic AI Engineer LLM Engineer RAG Pipeline Developer LLM Orchestration Multi-Agent Systems LangChain Developer LangGraph CrewAI AutoGen LlamaIndex Prompt Engineering ReAct Pattern Generative AI Developer OpenAI API Integration LLMOps AI Automation Engineer Autonomous Agents Agentic Workflow Automation Chain-of-Thought Reasoning AI-Assisted Development Vector Database Pinecone Weaviate Qdrant ChromaDB Embeddings Hybrid Search Semantic Search Reranking LLM Fine-Tuning Hire Backend Engineer FastAPI Developer Python Backend Engineer REST API Developer GraphQL Async Python Pydantic PostgreSQL Redis Microservices Architect Event-Driven Architecture Distributed Systems System Design High-Load Scalability API Architect Remote Docker Kubernetes CI/CD Cloud-Native Architecture AWS Serverless Deployment Automation Hire Developers Middle East Hire Developers Saudi Arabia Hire Developers Japan Hire Full-Stack Developer Next.js Developer React Developer TypeScript Full-Stack AI Integration Scalable AI Systems Business Automation Freelance AI Developer Remote Software Engineer Nepal Software Engineer Hire Remote Developer Production AI Platform Software Engineer For Hire Contract Developer Staff Augmentation Hire Offshore Developer Dedicated Developer Hire Senior Developer MERN Stack Developer SaaS Developer Build SaaS MVP SaaS Architecture Expert End-to-End Web Architecture Senior React Developer Senior Node.js Developer Multi-Tenant SaaS Developer NestJS Developer Node.js Developer Django Developer gRPC Developer OAuth JWT Security MongoDB Developer High Availability Engineer Latency Optimization Performance Optimization Senior Python Engineer API Gateway Engineer AI Chatbot Developer LLM Application Developer AI Solutions Architect Generative AI Engineer Semantic Kernel Haystack Developer LoRA Fine-Tuning MLOps Engineer vLLM Deployment Production-Grade AI Voice AI Developer Anthropic API Integration Observability Engineer Prometheus Grafana GCP Engineer Azure Developer Terraform API Integration Services Workflow Automation Specialist Stripe Integration Developer CRM Integration Developer Third-Party API Integration AI-Powered SaaS Builder Build AI Product AI for Fintech Healthcare AI Automation SaaS LLM Integration Automated Lead Generation AI Startup Developer Full-Stack AI Engineer Hire Full-Stack AI Engineer AI-Integrated Web App React + FastAPI Developer Next.js + Python Developer Senior Full-Stack Engineer MVP Development Expert Full-Stack for Startups AI Agent Developer AI Product Engineer Hire LangGraph Developer Hire CrewAI Specialist RAG Implementation Expert LLM Integration Expert On-Demand AI Engineer AI Automation for Business Ray Serve Engineer Model Evaluation Engineer Mistral Llama Fine-Tuner LLM Inference Optimization Microservices architecture AI backend architecture Backend system design Infrastructure as Code API design patterns Modular monolith vs services Database & caching Technical Leadership Engineering Portfolio Software Architecture Review Agile Development Expert Cross-Functional Team Lead PEFT Fine-Tuning Expert

Frequently Asked Questions

Straight answers if you're thinking about hiring me

Who is Ramesh Das?

I'm an Agentic AI Engineer and Backend Architect in Kathmandu, Nepal. For 6+ years I've shipped production AI platforms, RAG systems, multi-agent workflows, and FastAPI services. I lead AI at KLIKY AI on WinstaAI and take remote work with teams anywhere.

How do I start a remote project with you?

WhatsApp +977 9700864900 or email mrdasdeveloper@gmail.com. Tell me what you're building, when you need it, and any stack preferences. I take agentic AI, LLM orchestration, RAG, and backend jobs — usually with LangChain, LlamaIndex, and FastAPI.

What does “agentic AI” mean on a live product?

On WinstaAI it means agents that call tools, run multi-step jobs, switch models when needed, and support features like text-to-image, OCR, and media AI. Prompts alone aren't enough — you also need queues, credits, billing, admin controls, and GPU providers such as RunPod and FAL.ai.

What are your rates?

Hourly: $25 for full-stack and automation, $29 for AI and backend. Monthly retainer: $1,899–$1,999 for about 160 hours. Fixed work starts near $799 for automation, $1,199 for backend APIs, $1,899 for a SaaS MVP, and $1,999 for an AI agent or RAG build. Those figures already include a 50% direct-hire discount.

Can you build RAG or plug in GPT and similar models?

Yes. I set up RAG with embeddings and vector search (Pinecone, Weaviate, and similar) so answers come from your own docs. I also wire OpenAI and other LLM APIs into existing apps with auth, rate limits, and cost guards — the same approach we use in production SaaS.

What stack do you use most?

Python with FastAPI and Django; Node.js when it fits; React and Next.js with TypeScript on the front; PostgreSQL, MongoDB, and Redis for data; Docker, Kubernetes, CI/CD, and AWS or GCP to ship. That covers SaaS, microservices, and AI-backed web apps.

Do you do automation and API integrations?

Yes — scheduled jobs, queues, webhooks, Stripe, CRM hooks, and other third-party APIs. If Zapier or similar tools keep breaking, I usually move that logic into Python or Node with retries and monitoring.

Are you open to full-time, contract, or freelance?

All of the above: full-time remote, retainers, hourly, fixed-price, advisory, and staff augmentation. I work async with teams worldwide and stay reachable in English on WhatsApp, email, or whatever chat you already use.

WhatsAppPortfolio & hiring