I’m a Machine Learning Engineer with experience in building end-to-end Machine Learning and Deep Learning (NLP + CNNs ) projects, front and back-end web development, deploying containerized applications using docker, test-driven python programming using unit testing, bash scripting, visualization and ML DevOps in AWS and GCP.
TENSORFLOW, PYTORCH, KERAS, SKLEARN
MACHINE LEARNING
DVC, MLFLOW, DOCKER, TRAVIS CI, KUBERNETES
CI / CD
PYTHON, JAVASCRIPT, GO, UNIT TESTING
SOFTWARE ENGINEERING
EC2, S3, RDS, SAGEMAKER, COMPUTE ENGINE
AWS, G-CLOUD
Using Natural Language Processing, I built an arm that takes in voice commands and moves according to the command issued. This was achieved by using recurrent neural networks as the deep learning architecture.
Using asynchronous programming, I was able to fetch data from the usgs-lidar-public that contains cloud point data for various regions in the united states and convert that data into a geopandas dataframe and plot it on a 2D surface
This project involved both object detection and image classification using CNN i.e identifying malaria pathogens in a particular microscope generated image and classifying the image to either an infected sample or healthy sample.
Initializing and Maintaining AWS services (Dev Ops).
Building data ETL pipelines.
Developing, deploying and maintaining containerized applications.
Utilized Flask (a python framework) to build the back-end to a web-based fintech application.
Employed VUE js to build the front-end of the web application mentioned above.
Generated automated tests for the Enterprise Resource Planning Software using selenium.
Utilized Jenkins for automatic scheduling of tests.
I'm a holder of an bachelor's degree in Electronic and Computer Engineering from Jomo Kenyatta University of Agriculture and Technology, in Juja, Kenya. Some the courses offered include Calculus I through IV, Statistics, Control Engineering, Ordinary and Partial Differential Equations, Electromagnetics, programming languages e.g C, C++, SQL, MATLAB
Selected for the 10 Academy training offered for 12 weeks. The training involved building machine learning models for a new challenge weekly. Other data science concepts were also taught, they include data visualization, feature engineering, hyper-parameter tuning and reporting on the results from the models.
Attained a certificate in a deep learning course offered on the online platform coursera .The course scope included Sequence models, Convolution Neural Networks, Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization, Structuring Machine Learning Projects and Neural Networks and Deep Learning.
Earners of this certification have a fundamental understanding of IT services and their uses in the AWS Cloud. They demonstrated cloud fluency and foundational AWS knowledge. Badge owners are able to identify essential AWS services necessary to set up AWS-focused projects.