10 Academy profile site
Daniel Zelalem Zewdie
Addis Ababa, Ethiopia
ReactJS, React-Native, Angular, NodeJS
Full stack web and mobile applications development
Python, Java, C#
Object oriented programming
MySQL, Oracle-SQL, MongoDB
SQL, Non-SQL
Tensorflow/Kerasscikit-learn, RNN (LSTM, GRU), CNN. NLP, MlFlow, DVC, Kafka, Airflow
Machine Learning and Data Engineering
About me
A ML Engineer who takes pride in building models that translate data points into business insights with experience in executing data-driven solutions to increase efficiency, accuracy, and utility of internal data processing.
Education
BSc Software Engineering Addis Ababa University (2015-2020)
Achievements
Graduated with a major cumulative GPA of 3.85 / 4.0
Awarded a very great distinction certificate from Addis Ababa Institute Of Technology
Participated in the first AI/robotics project
Contributed in implementing a computer vision module for the robot perception
Implemented and deployed an encoder-decoder sequence to sequence translation model that translates Amharic sentences into Ethiopia Sign language
Courses taken:
Programming Related Courses:
Introduction to programming (Python), Object-Oriented Programming one (Java), Object-Oriented Programming two ( C#)
Software Engineering Related Courses:
Software Engineering one (Software development life cycle), Software Engineering two (Software testing), Software Project Management, Software Quality Assurance, and Testing
Computer System Related Courses:
System Programming (using a C programming language), Operating Systems, Computer Architecture, and Organization
Web application And Mobile Application Development Related Courses:
Web Design and Development (HTML, CSS, JavaScript, Node, Angular Framework, MongoDB)
Android Mobile Development
Database Related Courses
Fundamentals of databases (MySQL)
Advanced Database Management Systems (Oracle SQL)
Security Related Courses
Fundamentals of IT Security
Advanced IT Security
Data Science related courses:
Big Data (Using R)
10 Academy (2021-present)
Data Engineering and Machine Learning Engineering
Skills Gained
Business Understanding
Data Engineering
Data Understanding
Dashboard & Visualization
Statistics
MLOps & Continuous Delivery
Modeling and evaluation
Python programming
SQL programming
Career Thinking
Team working
Participating in community building activities
Work Experience
- Software Engineer | ML Engineer | Data Engineer, Grai Labs (Cape Town) (October 2021)
Designed, developed and deployed a customizable data collection software that can be used for any type of machine learning projects.
Designed an ETL pipe line for data collection
Maintained the development operation of the software on AWS cloud.
Have saved the Company's money by developing a data collection solution that replaced a costly AWS data collection service.
- Software Engineer, InfraNet (Addis Ababa) (April 2021)
Designed and developed a front end web application in ReactJs and React Native for a Telegram like application
Developed a front end mobile application using React Native / Expo.io
Developed a front end web application using ReactJs
Contributed in API integration using TDLib (a fully functional Telegram client)
Contributed in the development of a social media web application in a test-driven programming approach using ruby on rails framework
Produced a simple, easy to use user interaction design.
Contributed software engineering expertise in the development of the application from requirement gathering to deployment in a test environment.
Software testing using capybara
I Participated in a research project called Wheely which is the first robotics project in Addis Ababa institute of Technology. It is a research project to develop a self-driving and cleaning robot.
Contributed in implementing a computer vision module for the robot perception.
Implemented Ackerman steering mechanism in the navigation module.
Freelance Projects
- Feranka (Full Stack Developer)
I successfully designed and developed a web-based payment system app for a start-up team integrated with multiple third-party payment APIs through a common interface. The technologies used are ReactJs, Node/ExpressJs and MongoDB.
Developed a REST backend api using NodeJs/Express and MongoDB
Developed a frontend web based application in React and AntD
- Lemmaj.com (Front end Developer, BlackNile Tech)
Designed and developed a web-based application using React for a license driving organization.
Developed a front end application for users to register to a specific course package, schedule class and track course progress
Developed a front-end application for instructors to manage their students and update their student status.
Developed a front end admin application for the school administrators to manage their students and instructors
Integrated the front end application with loopback REST API
Projects
Amharic to Ethiopia Sign language Translator
A machine learning NLP pipeline system that translates Amharic sentences into Ethiopia Sign language. The system has 3 main components
A grammar translation model based on the encoder decoder seq2seq architecture, that translates Amharic Sentences into Ethiopian sign language sentences
A speech to text model for Amharic language
An application to present translated Ethiopian Sign language sentences in 3D animation.
Rossman Pharmaceutical Sales prediction
Applied machine learning models to forecast sales across multiple Rossman pharmaceutical stores.
SmartAd A/B testing
Design a reliable hypothesis testing to test if the ads that the advertising company runs resulted in a significant lift in brand awareness.
Used hypothesis A/B testing to test if a creative ad campaign resulted in a significant lift in brand awareness.
Applied machine learning approach for A/B testing and compared its result with the hypothesis A/B testing result.
TellCo User Data Analytics
Exploratory Analysis of Telecom Data. Descriptive and intuitive plots were generated and used to answer business questions.
This project was to analyze customer behavior in terms of their engagement, experience and satisfaction for a telecom company and suggest that if the company is worthy of buying or selling.
Amharic Speech Recognition
A Speech recognition model that transcribes Amharic speech to text.
Applied audio signal processing using librosa
Feature extraction for audio signal by generating Mel spectrograms
Using Tensorflow, I applied CNN with BI-directional RNN network to build a speech to text model.
Served the model using streamlit dashboard