Welcome to Ismael's freelance profile!
Location and workplace preferences
- Location
- Paris, France
- Can work onsite in your office in
-
- around Paris and 15km
Verifications
Freelancer code of conduct signed
Read the Malt code of conduct
Reputation
Loading...
Languages
Categories
Skills (38)
- Databases
-
Beginner Intermediate Advanced
- Data Science
-
Beginner Intermediate Advanced
-
Beginner Intermediate Advanced
-
Beginner Intermediate Advanced
-
Beginner Intermediate Advanced
-
Beginner Intermediate Advanced
-
Beginner Intermediate Advanced
-
Beginner Intermediate Advanced
Ismael in a few words
Ingénieur diplomé de Grenoble INP - ENSIMAG en 2014 avec 8 ans d'expérience professionnelle dont 6 ans d'expérience en Machine/Deep Learning et développement Python.
Ce sur quoi je peux vous aider :
- Analyse de données massives en Python avec Pandas / PySpark / Streamlit
- Développement et optimisation d'algorithmes et de modèles prédictifs (ML et DL Computer Vision et NLP)
- Développement Python (Data et DevOps)
Je suis dispo pour mission longue à temps plein, en remote et/ou sur site (région parisienne).
Ce sur quoi je peux vous aider :
- Analyse de données massives en Python avec Pandas / PySpark / Streamlit
- Développement et optimisation d'algorithmes et de modèles prédictifs (ML et DL Computer Vision et NLP)
- Développement Python (Data et DevOps)
Je suis dispo pour mission longue à temps plein, en remote et/ou sur site (région parisienne).
Experience
Allianz Trade France - Groupe Allianz
Banking & Insurance
Python developer - As a freelancer
Python development for batch and streaming processing.
CI-CD with GitLab / Docker / Bash / Python
CI-CD with GitLab / Docker / Bash / Python
Pernod Ricard - Pernod Ricard
Wine & Spirits
Data Scientist - Machine Learning Engineer - As a freelancer
Worked on optimization of promotional calendars (big Python codebase in production).
Future volumes sold for thousands of candidate promotional events are predicted with Gradient Boosted Trees (XGBoost), and then Mixed Integer optimization (PyOMO/Gurobi) is used to find the optimal subset of events which maximizes ROI given business constraints.
We use Azure DevOps for CI-CD and Azure ML to track our experiments and launch pipelines.
Future volumes sold for thousands of candidate promotional events are predicted with Gradient Boosted Trees (XGBoost), and then Mixed Integer optimization (PyOMO/Gurobi) is used to find the optimal subset of events which maximizes ROI given business constraints.
We use Azure DevOps for CI-CD and Azure ML to track our experiments and launch pipelines.
Crédit Agricole SA - Groupe Crédit Agricole
Banking & Insurance
Data Scientist - Image/NLP - As a freelancer
Worked on multimodal document classification and information extraction from scanned images and smartphone photos.
I built an information extraction Deep Learning model which performed really well on scanned documents (based on CNN + Transformer).
The information extraction deep learning model classifies each text box read by an OCR engine based on image (feature vector extracted by CNN) and text (feature vector extracted by Transformer).
I built an information extraction Deep Learning model which performed really well on scanned documents (based on CNN + Transformer).
The information extraction deep learning model classifies each text box read by an OCR engine based on image (feature vector extracted by CNN) and text (feature vector extracted by Transformer).
IDEMIA (ex Safran Morpho) - SAFRAN GROUP
Public Safety
Deep Learning Research Engineer - Computer Vision
I built Computer Vision Deep Learning models from scratch to analyze photos of ID documents (ID cards, passports and driver licences, for many countries).
The tasks I worked on were classification, localization, text detection, OCR and font recognition for anti-fraud.
I coded in Python and used libs like OpenCV, imgaug, Tensorflow and PyTorch to train neural networks and Tensorboard to follow model training.
I achieved very good results with synthetic training data and extensive data augmentation.
I often customized the neural networks, loss functions and metrics to maximize predictive performance.
I also implemented in Python a template alignment algorithm (based on RANSAC) to improve our text detection and OCR solutions.
The tasks I worked on were classification, localization, text detection, OCR and font recognition for anti-fraud.
I coded in Python and used libs like OpenCV, imgaug, Tensorflow and PyTorch to train neural networks and Tensorboard to follow model training.
I achieved very good results with synthetic training data and extensive data augmentation.
I often customized the neural networks, loss functions and metrics to maximize predictive performance.
I also implemented in Python a template alignment algorithm (based on RANSAC) to improve our text detection and OCR solutions.
AMADEUS
Travel & Tourism
Software/Machine Learning Engineer
I first worked about 2 years as a C++ backend engineer on reservation systems with high TPS and using a big Couchbase cache to store flights availabilities.
Then I joined the Research Optimization and Innovation team as a Data Scientist to work on improving Amadeus flight search product using Machine Learning.
I built a gradient boosted trees model to better rank travel solutions.
Then I joined the Research Optimization and Innovation team as a Data Scientist to work on improving Amadeus flight search product using Machine Learning.
I built a gradient boosted trees model to better rank travel solutions.
Recommendations
Check out Ismael's recommendations