Abdelaaziz Bellout

Rising Codementor

US$0.00

For every 15 mins

ABOUT ME

Recently graduated with a Master's degree in Data Engineer and Machine learning field after 10+ experience in IT Manager and Software development. Certified in IBM Big Data Engineer and IBM Artificial Intelligence Analyst. My strong-willed is building models that translate enterprise data into business insights.

Arabic, French, English

Casablanca (+01:00)

Joined August 2022

EXPERTISE

3 years experience

3 years experience

3 years experience

1 year experience

10 years experience

1 year experience

REVIEWS FROM CLIENTS

Abdelaaziz's profile has been carefully vetted and approved as a Codementor. Connect with Abdelaaziz now, and leave a review for them once you're done!

SOCIAL PRESENCE

GitHub

MyRobots

JavaScript

churn_ml

Jupyter Notebook

EMPLOYMENTS

Machine Learning Engineer (PT)

NeuralTeks

2022-11-01-Present

Trained computer vision models (YOLO) to detect and count microorganisms in laboratory industries, like bacteria and yeasts

Trained computer vision models (YOLO) to detect and count microorganisms in laboratory industries, like bacteria and yeasts
Used Data augmentation to overcome the lack of data
Evaluated computer vision models for accuracy and performance
Developed API using python, PyTorch, FastAPI and Nginx
Deployed the model on GCP Cloud and DigitalOcean using Bitbucket pipeline and Docker
Adept in defining APIs for user interface and model deployment
Communicate results with the key stakeholders and improve pipelines based on feedback
Define MLOps architecture for continual training and deployment of the model using Airflow, MLFlow and DVC
Reduce GPU training cost by 65% based on AWS spot instances

Git

Computer Vision

Docker

Git

Computer Vision

Docker

Google Cloud Platform

Deep Learning

Airflow

PyTorch

Fastapi

MLOps

DevOps

AWS (Amazon Web Services)

Python developer

OpenAI

2023-01-01-2023-03-01

Responsible for validating and ranking multiple ChatGPT AI model’s responses towards user’s queries.
Write high-quality a...

Responsible for validating and ranking multiple ChatGPT AI model’s responses towards user’s queries.
Write high-quality and optimal code in Python to solve the puzzle tasks to feed the AI models.
Provide necessary and clear explanations of the thought process/logic while writing the code in Jupyter notebooks.
Work with problem-solving to handle complex situations with ease
Debugging and creating necessary documentation
Do peer review of code and provide feedback

Python

SQL

Python

SQL

Machine Learning engineer

Whitesoft

2021-05-01-2022-07-01

• Tomato plant disease classification and detection using Deep Learning algorithm. • Preparing and labeling image datasets, • Training ...

• Tomato plant disease classification and detection using Deep Learning algorithm. • Preparing and labeling image datasets, • Training Convolutional Neural Network CNN model using Python, Keras framework and Google Colab notebook. • Comparing two Object Detection Models (Yolov5 and YOLOX). The Yolov5 based model had better accuracy, • Hyperparamter optimization was performed to tune the final model. • Converting the final weights to Tensorflow lite and deploying the model on Android Application using Android Studio.

Python

Machine Learning

Deep Learning

Python

Machine Learning

Deep Learning

TensorFlow

PROJECTS

Data pipeline using snowflake and airflow

2022

- Transfer data logs from AWS EC2 to AWS S3 using AWS KINESIS - Making ingestion data pipeline with Apache Airflow DAG using python and A...

- Transfer data logs from AWS EC2 to AWS S3 using AWS KINESIS - Making ingestion data pipeline with Apache Airflow DAG using python and AWS Managed Airflow (MWAA) - Loading data to Snwoflake data warehouse - Making all role management in AWS IAM and Snowflake

Amazon EC2

Snowflake

Apache Airflow

Amazon EC2

Snowflake

Apache Airflow

AWS (Amazon Web Services)

Yelp Dataset Analysis with Spark on Azure Databricks:

2022

- Created resource manager followed by storage account, the containers to upload the dataset - Created pipeline to copy data from Azure s...

- Created resource manager followed by storage account, the containers to upload the dataset - Created pipeline to copy data from Azure storage to Azure data lake storage ADLS using data factory - Created Azure Databriks workspace and cluster, access and configure ADLS from Databriks - Converted Data file format from JSON to Parquet and then to Delta format for smooth analysis - Upload dataset to Spark data frame format

JSON

Apache Spark

Databricks

JSON

Apache Spark

Databricks

Azure Data Factory