AI/ML ENGINEER · MECHATRONICS, FUT MINNA

Muhammad Inuwa Muhammad.
I turn raw signal into systems that ship.

I architect end-to-end ML pipelines — from k-space data and model design through to deployment — across medical imaging, robotics, NLP, and agentic AI. First Runner-Up at the RAIN × Meta AI Developer Academy Nigeria Hackathon, and a UN Millennium Fellow.

65+
Active bot users
13
Team led
#1
Runner-up, national hackathon
MIM
Building E2E-VarNet
Niger State, NG

Research depth, engineering discipline.

I'm an AI/ML Engineer and Mechatronics Engineering student at the Federal University of Technology Minna, focused on building intelligent systems that leave the notebook and reach real users. My core research is physics-informed deep learning for low-field MRI reconstruction — extending the End-to-End Variational Network with physics priors to make faster, more affordable scans viable in resource-limited settings.

I'm currently applying that same end-to-end discipline as an AI Robotics Engineer Intern at Coderina Edtech and a Machine Learning Intern at FlyRank AI, working across robotics, computer vision, and production ML pipelines. Earlier, I led a 13-person team building a road-hazard detection system, shipped a multilingual AI loan advisor for rural farmers, and scaled an agentic productivity bot to 65+ active users — each time owning the pipeline from data to deployment.

What I build with.

Deep LearningMachine Learning Computer VisionNatural Language Processing MLOpsGenerative AI MicrocontrollersRobotics Agentic AI

ML & Deep Learning

PyTorchTensorFlow Scikit-learnKeras XGBoostOptuna Hugging Face

Medical Imaging & Computer Vision

E2E-VarNetMRI Reconstruction k-space ProcessingCNN OpenCVSSIM / PSNR

NLP, Generative & Agentic AI

LLaMA 3.1Transformers LangChainLlamaIndex Whisper ASRRAG Prompt EngineeringMulti-agent orchestration

Data & Backend Engineering

PandasNumPy ETL PipelinesFastAPI MongoDBREST APIs

Cloud & DevOps

AWSGCP AzureLinux CI/CDFirebase RTDB

Robotics & Embedded Systems

ArduinoESP32 MicrocontrollersIoT Telegram Bot API

Education, work & recognition.

A quick path through where I've studied, worked, and been recognized.

2026 — PRESENT

AI Robotics Engineer, Intern Work

Coderina Edtech

Building an industrial-sorting robotic arm and an autonomous robotic dog; teaching AI fluency and LEGO Spike to young learners.

2026 — PRESENT

Machine Learning Intern Work

FlyRank AI · Remote

Building end-to-end machine learning and deep learning pipelines.

2022 — PRESENT

B.Eng, Mechatronics Engineering Education

Federal University of Technology Minna, Nigeria · 400 Level (In Progress)
2024 — 2025

AI Developer & Customer Support Work

Togo Mobility Limited

Delivered a production AI booking automation system that cut processing time by 60% and onboarded 20+ riders; provided bilingual (English/Hausa) support.

2025

First Runner-Up Award

RAIN × Meta AI Developer Academy Nigeria Hackathon

Nationally recognized for applied AI innovation and engineering excellence.

2025

Millennium Fellow Award

United Nations Academic Impact & Millennium Campus Network

Selected globally for leadership, innovation, and social impact contributions.

2024

Scholarship Recipient Education

Halima Ibrahim Babangida Foundation
2023

Community Manager & Customer Support Work

Jekaeat

Grew community engagement by 40% and resolved 95%+ of customer inquiries within SLA in a high-volume environment.

Projects that reached real users.

PyTorchE2E-VarNetMedical Imaging2025

Physics-Informed MRI Reconstruction for Low-Field MRI

Low-field MRI scanners produce noisy, low-resolution images with long scan times — a real barrier in resource-limited settings like Nigeria. I extended the End-to-End Variational Network with physics-informed priors from the MRI forward model, built a full k-space preprocessing pipeline with retrospective undersampling, and validated reconstruction quality across multiple acceleration factors using SSIM, PSNR, and NMSE.

0.86SSIM Achieved
↓ ScanTime enabled
3Eval metrics
// pipeline
k-space (undersampled)
  → retrospective mask
  → E2E-VarNet + physics prior
  → iterative refinement
  → reconstructed image
  → SSIM / PSNR / NMSE
02

Road Abnormalities Detector

Led a 13-member team to detect road cracks, potholes, and bumps from images for smart infrastructure use cases, evaluated on precision, recall, and F1.

PyTorchCNNOpenCV
03

Smart Motion Bin

An autonomous indoor robot that navigates to workstations on command, with a real-time web command center for telemetry and control.

JavaScriptFirebaseIoT
04

Multimodal AI Loan Advisor

Financial literacy AI for rural farmers, processing loan documents in 8 Nigerian languages via OCR, ASR, TTS, and an LLM risk-assessment engine.

LLaMA 3.1WhisperTesseract
05

ProDOS — Agentic Productivity Bot

An autonomous Telegram productivity bot scaled to 65+ active student users through progress logging and peer-competition features.

Agentic AIPythonTelegram API
06

AI Booking Automation System

A Telegram-based booking system for Togo Mobility, automating registration and payment verification — cutting manual booking time by 60%.

PythonPaymentsTelegram API

Let's build something.

Open to AI/ML roles, research collaboration, and interesting problems. Reach out directly, or use the form.

inuwamuhammad930@gmail.com +234 916 873 0302 linkedin.com/in/muhammad-inuwa-muhammad github.com/shadowboy-tech