Florian Elias

• As part of aircraft assembly, developed an NLP-based tool to categorize production anomalies based on their semantic meaning. 01/2022 – 07/2024 Lyon, France

• Optimized and restructured Spark data pipelines in line with MLOps best practices.

• Developed machine learning models to accurately predict aircraft speed using only engine parameters, in case of main probe icing.

• Developed and deployed a solution to automatically detect faulty pressure sensors (spatio-temporal series anomaly detection).

• Regularly presented progress and results to Airbus stakeholders.

• Taught Python and ML fundamentals to university students.

• Planned individualized lessons to meet student needs.

• Continuous self-learning through courses and certifications on topics such as MLOps or NLP.

• Participated in all aspects of machine learning projects to moderate images and videos: data acquisition, annotation and cleaning, training, evaluation, model deployment and maintenance. 01/2017 – 05/2019 Paris, France

• Facial recognition with a deep neural network: “facenet”.

• Face detection; celebrity and fake profile detection.

• Object detection with Faster-RCNN (weapons, hateful/offensive content etc.).

• Hate comment detection (Word2Vec, LSTM, Bert).