Mobirise
Amine Akrout

Hi, I am Amine, Data scientist with a strong background in statistical analysis and mathematics. I have extensive experience in solving real-world problems with the help of AI and Machine learning
I am problem-solving oriented with a keen ability to learn quickly and adapt to diverse settings
I can help you with every aspect of the data science workflow, including business understanding, data exploration, modeling, validation, deployment and monitoring.
My business intuition and communication skills allows me to make a quick impact and deliver high-quality results

       Skills    

Generative AI & RAG Systems

Development of intelligent conversational solutions, design of production-ready RAG architectures, fine-tuning of Large Language Models, system evaluation and optimization.

Machine Learning & Predictive Analytics

Implementation of supervised/unsupervised algorithms, advanced statistical modeling, feature engineering, model validation, and performance optimization.

MLOps & Productionization

ML model industrialization, training pipeline automation, production monitoring with drift detection, continuous deployment and versioning.

Data Exploration & Engineering

In-depth statistical analysis, handling of complex and large-scale datasets, anomaly detection, data visualization, and analytical storytelling.

Portfolio

AI Engineering & LLMOps

Customer Support Agentic RAG

An intelligent customer support system powered by LangGraph and LangChain that uses Retrieval-Augmented Generation (RAG) to provide accurate, context-aware responses to customer queries. Built with FastAPI, FAISS, and multi-stage validation for production-ready deployment.

Learn More >
AI-powered fashion recommendation system

AI-powered fashion recommendation system leveraging LLMs, embeddings, and retrieval techniques to deliver personalized shopping experiences.

Learn More >
AI-Powered Parenting Assistant (RAG)

An intelligent chatbot using LangChain, and OpenAI to provide safe, context-aware parenting advice. Served with FastAPI, it ensures accurate responses with real-time monitoring via Langfuse.

Learn More >

Machine Learning (MLOps)

End to end MLOps pipeline for Credit Card Default Prediction

Developed an end-to-end MLOps pipeline to predict credit card payment defaults. Utilized MLflow for model tracking, Prefect for workflow automation, FastAPI for model deployment, and Docker for containerization. Implemented model monitoring to ensure sustained performance.

Learn More 
MLOps on GCP with Cloud Run and Github actions

Training and deploying XGBoost as a web service Model with MLFlow, flask, Docker, Cloud Run and github actions.

Learn More 
MLOps with MLflow, App Engine and Github Actions

Training and deploying LightGBM Model with MLFlow, Fastapi, App Engine and github actions for mental health risk prediction

Learn More 
MLOps on Azure Cloud with Github actions

Training and deploying a TensorFlow DNN model on Azure Machine Learning and azure App Service for diamond price prediction.

Learn More 
MLOps on AWS with MLflow and Github actions

Training and deploying CatBoost Model with MLFlow, Flask, Docker, AWS ECS and github actions

Learn More 
Machine Learning Life Cycle management (MLOps)

Creating a Docker stack using MLflow, mysql and Minio to manage the lifecycle of TensorFlow models.

Learn More 

Big Data

Covid-19 Pandemic Effects On Airbnb

Creating a Data Lake on AWS, to analyze covid-19 effect on airbnb data and extract insights, using Spark and airflow

Learn More 
Real Time Big Data Analysis

Big Data Analytics using elasticsearch, logstash, kibana and kafka with real time streaming data of bike sharing API

Learn More 
Real time Twitter Sentiment Analysis

Sentiment Analysis and visualisation of tweets, using python, ELK, kafka and Docker

Learn More 
Spark Structured Streaming

End-to-end data workflow with kafka, spark streaming, postgres, superset and Docker

Learn More 

Data Science

Marketing Data Science

RFM Segmentation, Cohort Analysis, Market Basket Analysis and Customer lifetime value

Learn More 
Time Series Analysis

Benchmarking of different algorithms used fot time series forecasting (ARIMA, Prophet, LSTM)

Learn More 
Recommender System

Implemeting Recommender System using Deep Neural Networks architectures

Learn More 
House Price Web App

Deploying machine lerning app with Streamlit for house price prdiction 

Learn More 
Customer churn prediction

Machine learning based customer churn prediction model, created with pycaret and deployed using streamlit 

Learn More 

Deep Learning

Natural Language Processing

Deploying a Keras LSTM model with Flask and Docker for Spam detection 

Learn More 
Image Classification

Smoker Detection deep learning model served via a Web App using TensorFlow, tensorflow-serving, flask and Docker compose

Learn More 
Face recognition

Face Recognition and Identification using python, openCV and deep learning

Learn More 

Let's work together

If you want to have a chat with me about the portfolio, work opportunities or collaboration

‌

Drag and Drop Website Builder