Muhammad Tayyab Ilyas, Applied AI and Solutions Engineer based in Barcelona Open to Work

Muhammad Tayyab Ilyas

Applied AI & Solutions Engineer

Agentic Systems · LLM Integration · Workflow Automation · Production Deployment

I build and deploy agentic AI systems that automate real workflows: from multi-agent orchestration and MCP integrations to full-stack applications running in production.

Python Node.js LLM APIs MCP n8n Docker Linux

Barcelona, Spain · Open to Applied AI, AI Solutions, Automation and Forward Deployed Engineering roles

Founder of LoopCodeLab · PhD Researcher at UAB Barcelona

From problem to deployed system

I work end to end: I scope the real problem, design a practical AI solution, build the full-stack application, integrate the models and services, and deploy and operate it on my own Linux infrastructure.

Understand the problem. Turn operational and user needs into a clear, buildable AI solution.

Design AI solutions. Agentic workflows, multi-model routing, LLM-as-a-judge evaluation, tool calling and structured outputs.

Build full-stack. Complete applications across Python, Node.js, React and FastAPI.

Integrate everything. LLM APIs, REST APIs, MCP servers, WhatsApp, email and calendar, and automation tools like n8n.

Deploy and operate. Ship to Linux with Docker, Nginx, PM2 and systemd, with TLS, monitoring and failure handling.

Communicate clearly. Explain technical systems to business, research and education stakeholders so they get adopted.

Bridging applied AI and real-world delivery

I am an Applied AI and Solutions Engineer based in Barcelona. I design, integrate, evaluate and deploy production AI systems: agentic workflows, multi-LLM evaluation, real-time voice AI, MCP tools, AI media pipelines, and the full-stack applications and self-hosted infrastructure that run them.

My background combines engineering execution with doctoral research and more than ten years across education and technology. That mix lets me translate cleanly between business needs, user workflows and technical architecture, and to ship systems that non-technical teams can actually adopt.

Applied AI & Solutions Engineer

Independent · Since 2024

Design, build and deploy production AI systems and the infrastructure they run on

Founder & Creator

LoopCodeLab

Self-hosted multi-agent platform that plans, builds, reviews and ships software from a single prompt

Founder & CTO

PakEdX

AI education platform generating curriculum-aligned lesson plans and quizzes, built for Urdu and offline use

PhD Researcher

Universitat Autònoma de Barcelona

Pedagogical digital competence and AI adoption in higher education. Supervisor: Dr. Cristina Mercader

Writer & Columnist

Daily Urdu Columns

Author of 15 published Urdu columns on life, learning and society

Systems I have built and deployed

Three production systems that show the full arc: problem, architecture, integration, deployment and operation. Most run right now on infrastructure I manage myself.

Live at loopcodelab.com

LoopCodeLab: Multi-Agent Software Delivery

A self-hosted platform where planner, worker and reviewer agents turn a plain-language requirement into planned stories, parallel implementation, code review, Git integration and deployable software. Agents build in parallel on isolated git worktrees, a reviewer merges each change, and one idea ships to web, mobile and the app stores. Bring your own AI keys and own every line.

Multi-Agent Orchestration Model Routing & Retries Observable Sessions Self-Hosted · BYO Keys

Parallel agents over tmux and Git, with delivery to the App Store, Google Play and the Microsoft Store

Node.js · tmux · Flutter · React · Git · Multi-Agent CLIs
Deployed to Production

Paco: WhatsApp Voice AI Assistant

A real-time AI assistant that answers WhatsApp voice calls and holds a natural conversation. Paco checks email, calendar, weather and the web mid-call through live tool calls, and places outbound briefing calls through a simple HTTP API. Built from an empty folder to production in a single day.

Inbound + Outbound Calls OpenAI Realtime API Live Tool Calls Mid-Call Ops Dashboard

Deployed on my own Ubuntu server behind Nginx, with bidirectional audio streaming and a custom operations dashboard

Node.js · Puppeteer · WaVoIP · OpenAI Realtime API · PM2
Live on mcpservers.org

Cheema Text-to-Voice MCP Server

A free, open-source MCP server that gives AI assistants local text-to-speech and voice cloning. No API keys, no cloud, running entirely on your machine. Listed on mcpservers.org and consumable by any MCP client.

5 Built-in Voices 4 Languages Voice Cloning stdio/SSE/HTTP

Compatible with Claude Desktop, Claude Code, n8n and any MCP client

Python · MCP Protocol · NeuTTS · espeak-ng · MIT Licensed

Products, tools and integrations

A wider set of AI products, developer tools and integrations. Where a demo is public, the card links straight to the live system.

PakEdX

AI education platform that generates curriculum-aligned lesson plans, quizzes and personalised learning content for teachers and schools. Designed for Pakistani classrooms: Urdu support, print-friendly output and affordable delivery.

AI · Full-stack · Curriculum · Urdu · Offline-friendly

CAITA

Computer-Assisted Iterative Thematic Analysis: a three-stage qualitative-analysis workflow with structured coding, Excel exports and transparent researcher control. Published software with a DOI on Zenodo.

Python · Streamlit · Pandas · DOI 10.5281/zenodo.17474907
webtmux terminal dashboard in the browser

webtmux, the LoopCodeLab engine

The self-hosted engine behind LoopCodeLab. A browser and phone workspace where AI agents plan, build, review and ship whole projects in parallel, over xterm.js and a tmux PTY bridge. Live behind this link.

Node.js · xterm.js · tmux · PWA · systemd
Reel Room AI video studio

Reel Room

Transcript-first AI video editor: upload an interview, strike a line, and those seconds leave the cut. A hosted, mobile-first studio powered by OpenAI transcription and Remotion rendering across a seven-service Docker stack. Live behind this link.

React · FastAPI · Remotion · FFmpeg · PostgreSQL · Docker

MultiLLMChat

LLM evaluation studio: switch between Claude, GPT, Gemini, Groq, Qwen and DeepSeek, or compare two side by side with an automatic judge. Provider switching, error handling, retries and usage monitoring.

Python · Streamlit · LLM-as-a-judge · Multi-provider
RefLib reference library interface

RefLib

Reference manager for my PhD thesis: 590+ sources with client-side semantic search over embedded vectors and exports for citation tools. Live demo.

JavaScript · Embeddings · Vector Search

smart-name (npm)

Published npm package. Turns free text into a short, DNS-safe slug, safely fitting a clean project name into a single 63 character hostname label (RFC 1035). Zero dependencies.

Node.js · npm · Zero-dependency · RFC 1035
Snake Game built with Flutter running on an iPhone

APKIPA Build Pipeline

Flutter build and distribution pipeline on a headless server: hot-reloading web previews behind TLS and signed Android release APKs, plus a shipped cross-platform game.

Flutter · Android SDK · Nginx · Ubuntu Server

PakEdX WhatsApp Node for n8n

Custom n8n node connecting WhatsApp to automation workflows, running in a self-hosted Docker n8n stack alongside AI pipelines.

TypeScript · n8n · Docker · WhatsApp

OpenClaw in Production

Self-hosted, customised deployment of the OpenClaw open-source assistant, running as a daily-driver AI system on my own infrastructure.

Node.js · Multi-agent systems · Self-hosted

AI_Teacher

AI application that generates, manages and grades mathematics problems with personalised student feedback.

Python · Flask · scikit-learn · NLP

Everything here runs on infrastructure I operate

This site and its sister services are self-hosted on an Ubuntu server I administer: Nginx terminates TLS for more than a dozen subdomains, Node services run under PM2 and systemd, and n8n runs in Docker. The portfolio is the proof.

Internet · HTTPS Nginx TLS via Let's Encrypt Static sites portfolio · Reel Room · RefLib Node services Paco · webtmux · dashboard Docker n8n + custom nodes

What I work with

Applied AI

LLM APIs Agentic workflows Multi-agent orchestration Prompt & tool routing Structured outputs LLM-as-a-judge AI workflow automation

Integration

MCP REST APIs WhatsApp Gmail & Calendar n8n Webhooks

Development

Python Node.js JavaScript TypeScript React FastAPI Flask Flutter

Infrastructure

Docker Ubuntu Nginx systemd PM2 Cloudflare Self-hosted deployment

Research & Education

Educational technology Digital competence Mixed-methods research Learning analytics Instructional design Teacher training Pandas SQL

Next milestones: structured LLM-evaluation harnesses, retrieval over embedded corpora (already used client-side in RefLib), and richer observability across my agent workflows.

Independent Applied AI Engineer, 2024 to present

More than ten years across education and technology, including recent experience building and deploying AI and EdTech products. My engineering and my education work are shown separately below.

AI Engineering & Product

Independent AI Solutions Engineer

Since 2024

LoopCodeLab & AI Product Portfolio · Barcelona

  • Created LoopCodeLab, a self-hosted multi-agent platform where planner, worker and reviewer agents execute isolated tasks, review code, merge changes and ship working projects.
  • Built Paco, a production WhatsApp voice assistant integrating real-time AI conversation with email, calendar, weather, web search, outbound calling and an operations dashboard.
  • Built MultiLLMChat evaluation workflows: multi-provider routing, side-by-side comparison, automated LLM judging, retries and performance monitoring.
  • Developed Reel Room, a transcript-first AI video platform on FastAPI, Remotion, FFmpeg, PostgreSQL and a seven-service Docker architecture.
  • Published an open-source MCP server for local text-to-speech and voice cloning, and operate 15+ self-hosted sites and services on Ubuntu, Nginx, Docker, PM2 and systemd.

Founder & CTO

Since 2022

PakEdX · Remote

  • Designed and developed an AI education platform generating curriculum-aligned lesson plans, quizzes and personalised learning content for teachers and students.
  • Led end-to-end product work across user needs, AI workflows, full-stack implementation, deployment and educator validation.
  • Translated pedagogical requirements into features for teacher, school-leadership, assessment and reporting workflows.

Education & Research

PhD Researcher, Educational Technology

Since 2022

Universitat Autònoma de Barcelona · Barcelona

  • Research pedagogical digital competence, technology integration and AI adoption in higher education.
  • Conducted a mixed-methods study with 127 university-teacher survey responses and 32 semi-structured interviews, applying statistical and qualitative analysis.
  • Convert research evidence into practical recommendations for AI-enabled learning products and institutional implementation.

Assistant Education Officer (Contract)

2017 – 2022

District Education Authority, Gujranwala

  • Supported academic monitoring, curriculum implementation, teacher development and school coordination across assigned public schools.
  • Worked with teachers and school leaders to identify implementation gaps and communicate actionable support.

Teacher & Instructional Practitioner

2013 – 2017

Public Education Sector

  • Delivered classroom teaching and contributed to instructional planning, assessment and learner support.
  • Built practical understanding of teacher workload, resource limits and technology-adoption barriers now used to design teacher-facing AI products.

Built for AI in education

EdTech teams need engineers who understand classrooms as well as code. I bring both: education-sector experience, doctoral research and shipped AI products that teachers actually use.

Education-sector experience. Teaching, instructional design and district-level roles across public education.

Doctoral research. Pedagogical digital competence and AI adoption in higher education at UAB.

Curriculum & assessment. Real understanding of curriculum alignment, assessment and teacher training.

Evidence-based design. Digital-competence and learning-analytics research feeding practical product decisions.

AI product development. PakEdX lesson planning and assessment, plus AI_Teacher for maths practice and feedback.

Full-stack delivery. I build and deploy, so an EdTech idea reaches real teachers and students.

Research & publications

PhD Researcher · Universitat Autònoma de Barcelona · CRIEDO Research Group

Dissertation: Pedagogical digital competence and AI integration among university teachers in higher education. Supervisor: Dr. Cristina Mercader. My research supports evidence-based product design, user research and responsible AI adoption.

127 surveys · 32 interviews

A mixed-methods study of university teachers, combining statistical and qualitative analysis to identify adoption barriers and effective practices for AI-enabled learning.

  • From Technical Literacy to AI-Integrated Pedagogy: A Scoping Review of Digital Competence Frameworks for Higher Education (2000–2026)

    The Online Journal of Educational Technology (OJET) · Accepted with minor revisions, July 2026 issue

  • AI-Supported Lesson Planning for Teacher Education: A Capacity-Building Pilot at the University of Gujrat

    Project lead · UAB Fons de Solidaritat grant, EUR 1,500 (2026)

  • CAITA: Computer-Assisted Iterative Thematic Analysis (research software)

    Published with DOI 10.5281/zenodo.17474907

Licenses & certifications

When Floats Lie: Quantization, Performance, and Why Rust Keeps AI from Corroding

Rust Foundation

Quantization and numerical performance for AI systems

Signals you can verify

Published MCP server

Listed on mcpservers.org, MIT licensed

npm package

@tayyabcheema777/smart-name, zero dependencies

Software DOI

CAITA on Zenodo, 10.5281/zenodo.17474907

Peer-reviewed publication

Scoping review accepted at OJET, July 2026 issue

Research grant

UAB Fons de Solidaritat, EUR 1,500 (2026), project lead

15 published columns

Urdu columns at Daily Urdu Columns

Writing & communication

Alongside engineering, I write a regular Urdu column at Daily Urdu Columns, with 15 published pieces on life, learning and society.

Writing keeps my core professional edge sharp: explaining complex ideas simply. That is exactly what turns an AI concept into something a non-technical team will understand, trust and adopt.

Read the columns →

Let's build something

Looking for an engineer who can turn an AI concept into a deployed working system? Let's talk. Based in Barcelona, Spain, and open to Applied AI, AI Solutions, Automation and Forward Deployed Engineering roles.