Summary
Work History
Education
.
Websites
🏅 Certifications
💻 Skills
🗣️ Languages
Timeline
Generic

Kaoutar Chankhar

Data Engineer

Summary

Driven and results-oriented Data Engineer with a strong foundation in statistics, machine learning, and natural language processing. Skilled in data architecture, pipeline development, and end-to-end data engineering, with hands-on experience through self-directed learning and practical projects. Passionate about leveraging analytical skills to support data-driven decision-making and optimize business outcomes.

Work History

Stutter Enhancer Application

GitHub
- 2025
  • Developed an AI-powered speech enhancement application to assist individuals with stuttering by converting stuttered audio into fluent, clear speech.
  • Integrated local, resource-efficient AI models (Whisper for STT and Outetts for TTS) to process and enhance audio in real-time.
  • Built a scalable architecture using FastAPI, Celery, Redis, PostgreSQL, and MinIO for efficient audio processing and storage.
  • Deployed the app using Docker Compose for streamlined setup and management across environments

Freelance Developer - Backend API

- 2025
  • Developed and optimized a backend API to manage fitness club subscription data, client requests, and membership management processes.
  • Implemented secure authentication and authorization mechanisms using OAuth and JWT.
  • Integrated third-party services and databases to streamline data processing and retrieval.
  • Ensured robust error handling and logging for seamless debugging and maintenance.

Freelance Developer -Twitter Alert System

- 2025
  • Developed a real-time bot to monitor specific Twitter profiles and send instant alerts based on predefined conditions.
  • Utilized a third-party package to track user activity and deliver notifications via custom channels.
  • Allowed clients to personalize alerts based on profiles or keywords, ensuring timely and relevant updates.

Streaming Bike Data Application

GitHub
- 2024
  • Created a real-time application for bike station status and availability using the JCDECAUX API.
  • Streamlined data ingestion with Apache Kafka and processed it via Apache Spark Structured Streaming.
  • Visualized live data with a Streamlit app and deployed using Kubernetes on a local cluster with Kind.

Kaggle Chatbot Application

GitHub
- 2024
  • Developed a chatbot for answering Kaggle competition inquiries using LangChain for data processing and a Mistral model for generating responses.
  • Leveraged Retrieval-Augmented Generation (RAG) to provide context-driven responses by retrieving relevant information from external sources.
  • Built a FastAPI backend for handling requests and a Streamlit front end for seamless real-time user interaction.

Freelance Data Scientist

- 2024
  • Collaborated closely with stakeholders to define explicit and implicit requirements, leveraging both experience and domain knowledge.
  • Analyzed and decoded a large dataset to provide actionable insights for informed decision-making using machine learning and data analysis techniques.


Kaggle Competitor

2021 - 2025
  • Developed and implemented data-driven models to solve real-world problems in a competitive setting, utilizing advanced machine learning techniques.
  • Collaborated with team members to analyze datasets, optimize algorithms, and improve model performance to achieve high-ranking results.

Data scientist Intern

IRIDIA Laboratory, Erasmus Hospital
- 2019
  • Developed a data preprocessing pipeline to extract features from raw heart rate data and built a machine learning model that detects paroxysmal atrial fibrillation with 90% accuracy, diagnosing 9 of 10 true positives faster than cardiologists' ECG analysis

Data analyst Intern

Gaya Research Services
- 2018
  • Conducted a statistical analysis plan for a clinical trial of a new stroke treatment
  • Designed a scoring model for stroke risk using multiple correspondence analysis, achieving results comparable to the Framingham Stroke Risk Score

Statistician Intern

Ministry of Economy and Finance
- 2017
  • Applied Hodrick-Prescott and Baxter-King filters, along with a production function model, to estimate potential growth and output gap of the Moroccan economy using macroeconomic data.

Education

Specialized Master in Data Science, Big Data

Université Libre De Bruxelles

Master of Science in Statistics-Applied Economics

National Institute of Statistics-Applied Economics

Classes Préparatoires Aux Grandes Écoles MP

Lycée CHARIF EL IDRISSI

.







.

🏅 Certifications

Azure Data Scientist Associate, Microsoft

https://learn.microsoft.com/api/credentials/share/en-us/kaoutarchankhar

-7724/db7482728c4f2d9?sharingId=4787E69D047D60C6

💻 Skills

Programming Languages

  • Python
  • R


SQL/NOSQLSQL

  • SQL
  • MongoDB


ETL

  • Apache kafka
  • Apache spark
  • Apache airflow


Deep Learning Frameworks

  • HuggingFace
  • Pytorch
  • TensorFlow
  • Keras


Machine learning Frameworks

  • Scikit-learn
  • XGBoost
  • LightGBM


Web Frameworks

  • FastAPI
  • Streamlit


Cloud

  • AWS
  • Azure


Workflow Orchestration

  • Docker
  • Kubernetes
  • GIT
  • Linux shell

🗣️ Languages

  • English
  • French
  • Arabic

Timeline

Stutter Enhancer Application

GitHub
- 2025

Freelance Developer - Backend API

- 2025

Freelance Developer -Twitter Alert System

- 2025

Streaming Bike Data Application

GitHub
- 2024

Kaggle Chatbot Application

GitHub
- 2024

Freelance Data Scientist

- 2024

Kaggle Competitor

2021 - 2025

Data scientist Intern

IRIDIA Laboratory, Erasmus Hospital
- 2019

Data analyst Intern

Gaya Research Services
- 2018

Statistician Intern

Ministry of Economy and Finance
- 2017

Specialized Master in Data Science, Big Data

Université Libre De Bruxelles

Master of Science in Statistics-Applied Economics

National Institute of Statistics-Applied Economics

Classes Préparatoires Aux Grandes Écoles MP

Lycée CHARIF EL IDRISSI

Similar Profiles

CREATE PROFILE
Kaoutar ChankharData Engineer