MA

Available for new projects

Hello! I'm

Maarij
Aqeel

I build voice AI agents, AI automations and production-ready AI products for teams worldwide.

An AI Engineer, A Full-Stack Dev, An LLM Engineer
Maarij Aqeel
Maarij Aqeel

About me

I'm Maarij, a Full-Stack AI Engineer working remotely with teams worldwide. Most AI features die in the gap between a demo and real users. I build both halves: the AI system and the product around it, so what ships keeps working under real traffic.

Built for

MelonLabs16x9.ai

lower conversational-AI costs
80%lower conversational-AI costsWordBuddy AI
less time to produce content
95%less time to produce content16x9.ai
lower hosting costs
60%lower hosting costsWordBuddy AI

Services

What I build

Three ways I help teams ship AI that works in production, not just in a demo.

01

Voice AI agents

Real-time voice agents that talk to your customers, learners or candidates, and stay affordable at scale.

  • Tutors, receptionists and interviewers
  • Speech-to-text, LLM and TTS pipelines tuned for latency
  • Booking, CRM and knowledge-base integrations
02

AI automation & agents

Workflows and agents that take repetitive work off your team, from research to publishing.

  • n8n and LLM workflow automation
  • AI agents that act on your data and tools
  • Retrieval (RAG) over your own documents
03

AI product builds

From idea to a shipped, full-stack AI product: web, mobile and the backend behind it.

  • Next.js, Python and mobile apps with AI built in
  • Databases, auth, payments and CI/CD
  • Launch, app-store release and hosting cost control

Selected Work

01

WordBuddy AI

Voice AI · MelonLabs

Shipped to Google Play with 80% lower conversational-AI costs.

Capacitor · LiveKit · Deepgram · ElevenLabs · Gemini · SQLCipher

WordBuddy AI preview
02

AI Content Automation Engine

AI automation · 16x9.ai

Cut content production time 95% with four chained n8n workflows.

n8n · LLMs · Google Trends

AI Content Automation Engine preview
03

Intervue AI

Voice AI · Web app

Real-time AI interviews with 80% lower voice costs and 30% faster setup.

Next.js · LiveKit · Deepgram · Cartesia · DeepSeek · Supabase

Intervue AI preview
04

NL-CAD

AI engineering · Text-to-CAD

Plain English to CAD models: 46/46 eval cases pass at about $0.01 each.

Python · CadQuery · FastAPI · OpenRouter

NL-CAD preview
05

Data Analyst Agent

AI agent · Live demo

Ask your data questions in plain English: reports, anomalies and forecasts.

FastAPI · Next.js · pandas · Jupyter · OpenRouter

Data Analyst Agent preview

Want to see more?

Explore all of my projects and creations

See all works

Process

How we'd work together

Clear scope, working software every week, and no surprises.

  1. 01

    Discovery call

    We talk through the problem, your users and what success looks like.

  2. 02

    Scope & fixed quote

    You get a clear plan, milestones and a fixed price for the first build.

  3. 03

    Build with weekly demos

    You see working software every week, not a big reveal at the end.

  4. 04

    Launch & support

    I ship to production, hand over cleanly and stay on for fixes and next steps.

Ways to work together:Fixed-scope buildMonthly retainerConsulting call

My career &
experience

  1. Full-Stack AI Engineer

    MelonLabs Ltd · Contract · Mar 2026 – Present

    Now

    Building WordBuddy AI, an English-learning platform for Southeast Asian learners. Took it from web app to a Capacitor + Phaser.js mobile app on Google Play, cut hosting costs 60% and conversational-AI costs 80%, and rebuilt offline-first storage on encrypted SQLite with delta sync.

  2. Technical Team Member — AI/ML

    GDGOC FAST NUCES · Part-time · Sep 2025 – Present

    Now

    AI/ML technical team at Google Developer Groups on Campus, FAST NUCES.

  3. AI Automation Engineer

    16x9.ai · Contract · Oct 2025 – Feb 2026

    2026

    Built an AI content automation engine of four n8n workflows (research, generation, media processing, publishing) that cut content production time 95%, and a Vapi voice receptionist with Airtable-backed knowledge, appointment booking and call routing.

  4. AI Engineer Intern

    DevelopersHub Corporation · Internship · Jul – Sep 2025

    2025

    Developed a personalized AI chatbot with context-aware responses and user-specific conversation flows, and used few-shot prompting to make LLM output more consistent and accurate across task-specific workflows.

  5. Full-Stack Developer Intern

    Nexium · Internship · Jul – Aug 2025

    2025

    Architected the Intervue AI backend with dual-role auth, cutting voice costs 80% and interview setup time 30% (Next.js, LiveKit, Deepgram, Cartesia, DeepSeek), and shipped an AI blog summarizer that cut content review time 75%.

Tech stack

The production tools I ship with, from voice AI to deployment.

Python
TypeScript
JavaScript
React
Next.js
Node.js
FastAPI
Django
Tailwind CSS
Capacitor
PyTorch
TensorFlow
Hugging Face
LangChain
Ollama
Google Gemini
OpenRouter
scikit-learn
LiveKit
Deepgram
ElevenLabs
n8n
Make
Zapier
PostgreSQL
MongoDB
Redis
Supabase
Docker
Git

Testimonials

What clients say

4.5
“Maarij completely re-architected our conversational AI pipeline. Not only is the new voice agent lightning-fast, but it actually slashed our operating costs by 80%. Finding an engineer who understands how to build for scale—and not just a quick demo—is incredibly rare. Highly recommended.”
David ChenTechnical Co-Founder
5.0
“The custom n8n automation engine he built saved our editorial team hundreds of hours. He doesn't just plug into basic APIs; he builds chained workflows that can handle weird edge cases and real-world data without breaking. A massive upgrade to our internal operations.”
Sarah JenkinsDirector of Operations
4.0
“Working with Maarij was a breath of fresh air. Instead of waiting months for a massive, buggy release, we had working software in our hands every single week. He took our messy LLM concept and shipped a polished, fully integrated Next.js application that our users actually love.”
Marcus VanceProduct Lead
4.0
“Finding a developer who deeply understands both machine learning infrastructure and complex offline-first mobile databases is hard to come by. Maarij bridged that gap perfectly. The synchronization architecture he deployed for our app is rock-solid.”
Elena RodriguezCTO
“Most developers can build a quick wrapper around an LLM, but very few know how to make it survive real user traffic. He scoped the project clearly, communicated relentlessly, and delivered a production-ready application exactly on schedule.”
James CarterTeam Lead
4.5
“Maarij completely re-architected our conversational AI pipeline. Not only is the new voice agent lightning-fast, but it actually slashed our operating costs by 80%. Finding an engineer who understands how to build for scale—and not just a quick demo—is incredibly rare. Highly recommended.”
David ChenTechnical Co-Founder
5.0
“The custom n8n automation engine he built saved our editorial team hundreds of hours. He doesn't just plug into basic APIs; he builds chained workflows that can handle weird edge cases and real-world data without breaking. A massive upgrade to our internal operations.”
Sarah JenkinsDirector of Operations
4.0
“Working with Maarij was a breath of fresh air. Instead of waiting months for a massive, buggy release, we had working software in our hands every single week. He took our messy LLM concept and shipped a polished, fully integrated Next.js application that our users actually love.”
Marcus VanceProduct Lead
4.0
“Finding a developer who deeply understands both machine learning infrastructure and complex offline-first mobile databases is hard to come by. Maarij bridged that gap perfectly. The synchronization architecture he deployed for our app is rock-solid.”
Elena RodriguezCTO
“Most developers can build a quick wrapper around an LLM, but very few know how to make it survive real user traffic. He scoped the project clearly, communicated relentlessly, and delivered a production-ready application exactly on schedule.”
James CarterTeam Lead

FAQ

Questions, answered

Anything else? Ask the AI assistant in the corner or send a message below.

What kind of projects do you take on?

Voice AI agents, AI automations and agents, and full-stack AI products: from a focused prototype to a production app with the backend, database and deployment around it.

How does pricing work?

It depends on scope. Discovery and prototype work is quoted as a fixed price; ongoing product work is a monthly retainer. Send a short brief and a budget range and you'll get a scoped estimate rather than a generic rate card.

Do you work with clients outside Pakistan?

Yes, remote-first. I work from Pakistan (UTC+5), which overlaps with EU mornings and US East Coast mornings, and I'm flexible for standups.

Can you work with our existing team and codebase?

Yes. I can own a feature end to end or work inside your repo, reviews and release process alongside your engineers.

Will you sign an NDA?

Yes. Happy to sign an NDA before we discuss details.

How do we get started?

Hit "Book a call", share a few details about your project, then pick a time that suits you in my calendar. I'll come to the call already knowing what you need.

Maarij Aqeel