Skip to content
View Yared-Mengiste's full-sized avatar
🎯
Focusing
🎯
Focusing
10 followers · 8 following

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Block or report Yared-Mengiste

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Yared-Mengiste/README.md

Hi, I'm Yared Mengiste

Full-Stack Developer & AI/ML Engineer

GitHub · LinkedIn · Email · Instagram

I'm a full-stack developer and AI/ML engineer based in Addis Ababa, Ethiopia.

I build production web applications and applied machine learning systems. My full-stack work focuses on backend systems, data-driven applications, and clear user experiences. In AI/ML, I work with retrieval-augmented generation, computer vision, predictive coding, and neural networks implemented from first principles.

I'm currently an AI/ML Intern at iCog Labs, working on applied research involving RAG systems, predictive coding networks, YOLOv8 object detection, category theory, and probabilistic logic networks.

I design and build whatever I can imagine.

Featured Work

Project Description Stack
Taxi Pay An offline-first Android app for Ethiopian taxi drivers that auto-captures teleBirr SMS payments, tracks cash fares and fuel expenses, and shows daily/weekly/monthly earnings dashboards — no backend, no cloud. Flutter, Dart, SQLite
Bello Restaurant Menu & Delivery A production restaurant web application focused on an accessible menu and ordering experience. Full-Stack, Web
PPE Detection with YOLOv8 Detects workers and verifies required safety equipment using a model trained on a Roboflow dataset. Python, YOLOv8, Computer Vision
Traffic Accident Neural Network Classifier Classifies traffic accident types using cleaned and engineered real-world data. Python, Neural Networks, scikit-learn
RAG + Ragas Evaluation Pipeline A modular RAG pipeline built with LangChain and evaluated with Ragas and Mistral AI models. Python, LangChain, Ragas
FreshCart A grocery delivery platform connecting customers with nearby supermarkets. Spring Boot, REST API, Web, React
BookShare A platform for uploading, searching, sharing, and downloading books and PDF files. JavaScript, Full-Stack

Tech Stack

Frontend
React · Tailwind CSS · JavaScript · HTML5 · CSS3 · Blade

Mobile
Flutter · Dart

Backend
Spring Boot · Laravel · Node.js · Express · Flask

AI / ML
PyTorch · LangChain · Ragas · YOLOv8 · RAG Systems · Predictive Coding Networks · Neural Networks from Scratch

Languages
Python · Java · JavaScript · Dart · C# · PHP

Databases
MySQL · PostgreSQL · MongoDB · SQLite

Tools
Git · GitHub · VS Code · IntelliJ IDEA · Postman

Certifications

  • Scientific Computing with Python — freeCodeCamp
  • Machine Learning Specialization — DeepLearning.AI / Stanford University
  • Deep Learning Specialization — DeepLearning.AI

Education

Bachelor's Degree in Computer Science
HiLCoE School of Computer Science & Technology

Currently Exploring

  • Reliable retrieval-augmented generation systems and evaluation
  • Predictive coding architectures trained without standard backpropagation
  • Computer vision and object detection
  • Scalable full-stack systems and intelligent applications
  • Offline-first mobile apps with Flutter

Connect

I'm open to conversations about full-stack development, applied AI/ML, research, and collaborative projects.

Code. Create. Learn. Repeat.

Pinned Loading

  1. Freshcart_Backend_With_Spring Freshcart_Backend_With_Spring Public

    This is the backend API for the FreshCart e-commerce platform – a grocery delivery app that connects customers to nearby supermarkets offering fresh animal and plant-based products.

    Java

  2. robelnigusse/share-knowledge robelnigusse/share-knowledge Public

    book sharing and downloading platform

    JavaScript

  3. traffic-accident-neural-network-classifier traffic-accident-neural-network-classifier Public

    A neural network model built to classify traffic accident types using cleaned and engineered features from a large real-world dataset, with careful preprocessing and validation to prevent overfitti…

    Jupyter Notebook

  4. cross_entropy_implementation cross_entropy_implementation Public

    Understand cross entropy in use of loss function and create a custom cross entropy function to train a model on fashion MNIST dataset

    Jupyter Notebook

  5. ppe_detection_yolov8 ppe_detection_yolov8 Public

    This project implements a Personal Protective Equipment (PPE) detection pipeline using YOLOv8. It trains a model on a Roboflow dataset to detect workers and determine whether required safety gear i…

    Jupyter Notebook

  6. taxi-pay taxi-pay Public

    Taxi Pay is an offline-first Android app designed for Ethiopian taxi drivers to seamlessly track teleBirr SMS payments, cash fares, and fuel expenses during active work shifts — complete with daily…

    Dart