About Me
Hi I am Clément Delteil
,
I recently finished my end-of-study internship at namR as a Data Scientist where I engineered a methodology to filter noisy labels from training sets, resulting in the improvement of data quality and model performance 📈. I’ve also developed a meta-model (LightGBM + KNN) to predict the use type of France’s 34 million buildings 🏙️ from extremely unbalanced spatial data.
I’m now looking for a full time position in Paris as a Data Scientist / Machine Learning Engineer.
I hold a Canadian
M.Sc in Artificial Intelligence from the UQAC as well as a French
Computer Science Engineering Degree with a focus on Data Science and Artificial Intelligence from the UTBM.
You can find my CV in French and in English in the Resume section of this website.
More personally, this site is both a portfolio and a personal site where I can share my pictures, my readings or articles on some AI and Data Science topics I like. Traveling is an integral part of my personal life and my school curriculum, I spent 1 year in Slovenia with an internship and an exchange semester and now 1 year in Canada. Outside of that I had the chance to travel to many countries:
…
To conclude on my person, I live by the latin adage : “Mens sana in corpore sano “. I run 🏃🏻, read 📔, lift weights 🏋🏻 and sometimes yes, I sit in front of my computer 👨🏻💻. These activities help me keep clear ideas for my projects and my life ! Feel free to browse through the site, I have shared photos and projects from my journey.
Data Science
Pandas, Numpy, PySpark, NLTK
Tableau, PowerBI, Matplotlib
scikit-learn, MLlib, Spark Streaming, XGBoost
Working experience
👨💻 Data Scientist
namR
• Paris, France
July 2023 — January 2024
End of study internship - Addressing climate issues with Data Science - Recommandation Letter 📜
As part of a team of 7 people, developed Machine Learning models, and worked on R&D topics about noise detection in ML labels on subjects related to the green renovation of buildings and the ecological transition.
- Developed a method to filter noisy labels from training datasets via Confident Learning, thus improving data quality and model performance.
- Developed a Meta-Model (LightGBM + KNN) to predict the type of France's 34 million buildings (Residential, Tertiary, Industrial, Agricultural).
- Worked in Agile mode and regularly presented results to other Data Scientists and Data Engineers.
- Improved the internal repository by modifying the Gitlab CI through the addition of various linters and typing.
- Optimized SQL queries on PostgreSQL to process millions of spatial data.
- Regular company-wide presentations on technical subjects (Confident Learning, LLM, etc.).
Data ScienceDataikuPostgreSQLMachine LearningData AnalysisR&DCommunicationLarge Language Models
📝 Technical Writer
January 2023 — Present
Freelance - Writing technical articles on the Medium platform.
- Interested more than 35,000 readers by writing 18 articles on various Data Science topics, guided by my curiosity.
-
Keynote Speaker at the Google Student Developer Club ML Summit; inspired over 80 participants by sharing my personal journey in Data Science and AI, motivating their active engagement and public contributions.
- Demonstrated to students the need for Quantization of models with limited resources (i.e. standard GPUs) and a fine-tuning experiment for text and article summary generation.
Data ScienceCommunicationLarge Language ModelsDeep LearningNatural Language Processing
👨🏻🏫 Teaching Assistant
UQAC
• Chicoutimi, Canada
February 2023 — April 2023
Part-time work - Correction of Bachelor's degree students' work - Recommandation Letter 📜
-
Algorithmic - Complexity analysis, recurrence, Djisktra, Divide and Conquer strategies, etc.
-
Machine Learning for Data Science - Verification that the correct development steps of a machine learning project are followed.
PythonScikit-LearnTensorFlowJupyter NotebookPrecisionRigor
🚀 Research Assistant
September 2021 — February 2022
Six-month internship as an assistant engineer - Recommandation Letter 📜
Assisted researchers and PhD students in their Human-Computer Interaction projects.
-
Preprocessing - Used Optical Character Recognition (OCR) and Natural Language Processing (NLP) to preprocess thousands of text files for machine learning algorithms.
-
Data Collection - Built a 3000 movie/script dataset by scraping online from different sources for Elham Motamedi's research project on the Detection of Hedonic and Eudaimonic Movies Characteristics from Scripts.
-
Data Scraping - Developed a GUI/Cron tool to automatize the collection of tweets from Twitter under Marko Tkalčič supervision.
-
Plagiarism Detection - Developed a Python tool that detects plagiarism between several files and presents its results in a table. It shows side-by-side comparisons of texts where similar sentences between documents are highlighted.
-
Conference - Attended HCI SI 2021 conference (Psychophysiology, User Gullibility, Behavioral Authentification, Music Retrieval and Recommendation...)
PythonResearchOCRNLPSeleniumTkinterScikit-LearnBERT
📚 Library Monitor
UTBM
• Belfort, France
October 2020 — June 2021
Part-time work during my studies.
- Tidied books.
- Helped students and professionals with documentary research.
- Ensured compliance with library regulations.
- Redesigned of bookshelf signage.
PunctualityOrganisational CapacityAttentivenessCreativity
🥼 Laboratory Technician
January 2019 — February 2019
One-month worker internship as part of my engineering training.
- In charge of the comparison of Volatile Organic Compound analysis methods on particle board between the percolator and the Gas Analysis. The purpose of this comparison was to enter a new standard.
PunctualityRigorPrecision
Education
🎓 M.Sc in Computer Science
UQAC
• Chicoutimi, Canada
September 2022 — February 2024
Dual degree in the context of an agreement established with the UTBM.
Specialization in Artificial Intelligence
Current CGPA 4,22/4,30.
- Machine Learning for Big Data (A+)
- Artificial Intelligence (A+)
- Business Intelligence Principles and Methods (A+)
- Advanced Data Structures and Algorithms (A+)
- Computer Vision and Image Processing (A+)
- Deep Learning (A)
- Practical Workshop in Artificial Intelligence (A+)
PythonC++JavaPyTorchTensorFlowTableauPowerBI
🎓 Computer Science Engineer
UTBM
• Belfort, France
September 2018 — February 2024
Specialization in AI and Data Science
Last semester's GPA in Data Science 98/100 (Maximum grade is A).
- Data Science (A)
- Business Intelligence Big Data (A)
- Database optimization (A)
- Business English (A)
- Human Computer Interaction (B)
- Optimization and Operational Research (B)
- Parallel Computing and Multicore Architecture (B)
PythonCSQLPowerBISQL ServerMySQL
🌅 Semester Abroad
FAMNIT
• Koper, Slovenia
February 2020 — July 2020
Study term abroad (6 months), mathematics and computer science courses in English.
AlgebraCalculusEnglishHTMLCSS
👨🏼🎓 Highschool Student
September 2015 — June 2018
French High School National Exam obtained with the European Mention certifying a significant investment in my subjects in English (mathematics in English as well as an extra hour of English in euro group)
English
Certifications
More certifications and Badges are available on my LinkedIn page.