Machine Learning Engineer

• Sep 2022 - Present

Jr. Machine Learning Engineer

• Jan 2021 - Sep 2022

Data Scientist

• Nov 2019 - Nov 2020

➤ Data Science consulting for Bristol Myers Squibb on a machine learning classification project predicting patients’ retention to a specific drug. This project was featured in the American College of Rheumatology (ACR) and AI for Health conferences in November 2020. ➤ Exploration and processing of clinicaltrials.org database with NLP techniques and advanced analysis of textual data. This innovative project was eligible to the French Tax Credit Research. ➤ Development and teaching of a Python training program. Also performed Data Science vulgarization and initiation for collaborators and clients Show less

Bioinformatics Data Scientist - ML improvement of CRISPR sgRNA design

• Mar 2018 - Aug 2018

6 months Master's internship in the Perrimon Lab at Harvard Medical School, Genetics Department. Subject : ⇒ Machine Learning predictions of CRISPR/Cas9 on-target efficiency in Drosophila melanogaster This project aimed to provide the Drosophila RNAi Screening Center (DRSC) with an accurate CRISPR sgRNA efficiency scoring tool in order to improve the sgRNA design pipeline. I used Machine Learning algorithms to model the efficiency of sgRNAs targeting essential genes, based on their characteristics, in a D.mel genome-wide pooled CRISPR screen. The Machine Learning models identified were implemented in a command-line tool with which single or batch sgRNA efficiency predictions can be made from the raw sgRNA sequence (see GitHub link). Skills : ➤ Programming and Machine Learning in Python and R ➤ CRISPR/Cas9 genetic engineering, molecular genetics and genomics ➤ Scientific literature review, autonomy, public speaking, GitHub version control Show less

Bioinformatician - High throughput data analysis

• Jul 2017 - Aug 2017

Two months internship in the Laboratory of Theoretical Physics and Condensed Matter. (LPTMC - UMR CNRS 7600) Subject : ⇒ Expressed genes domain identification of different cell types by high-throughput data analysis. I helped in the development of a machine learning pipeline to infer the best preprocessing method to detect expression signals in complex datasets. The datasets' cell types are then to be clusterized into large cellular groups (brain, blood, gut, etc...) according to their presumed expression pattern (unsupervised machine learning). Skills : ➤ Python programming (Jupyter, NumPy, pandas, Scikit-Learn, Matplotlib etc...) ➤ Handling very large datasets (over 250Gb of RAM) ➤ Data cleaning, visualization and processing (.bed/.hdf5, large arrays, sparse matrix etc...) Show less

Bioinformatician - Comparative genomics

• Apr 2016 - Jul 2016

Internship in the Atelier de BioInformatique (ABI - UMR 7205) in the National Museum of Natural History. Subject : ⇒ Comparative Genomics characterization of Salmonella enterica serovar Dublin strains implicated in osteo-articular infections. Three pathogenic bacterial strains were harvested from hip prosthesis infections. The goals were to used bioinformatics and comparative genomics tools to : ➤ Develop of a Multi-Locus Sequence Typing script (Python) to confirm the strains' serotype (Salmonella enterica serovar Dublin) ➤ Identify genomic rearrangements (recombination, viral insertion, genomic reduction) with MAUVE (Multiple Genome Alignment) and/or ACT (Artemis Comparison Tool) ➤ Establish the phylogeny analysis of the strains ➤ Identify specific gene/region that would explain the enhanced colonization/virulence of the strains Show less

Molecular Geneticist - Drosophila metabolism

• Jun 2015 - Aug 2015

Two months internship in the Growth and Metabolism of Drosophila team of the Institute of Integrative Biology of the Cell (I2BC - UMR 9198) Subject : ⇒ Characterization of lipid metabolism and genetics of Drosophila. ➤ Genetic markers recognition in larvae and adult Drosophila to identify different genotypes ➤ Crossbreedings techniques and drosophila stocks management ➤ Spectrophotometry analysis of the lipid content of several drosophila genotypes at different larvae stages. Show less

Student Jobs

• 2011 - 2015

Part-time English teaching/baby-sitting or summer jobs in different places to finance my studies. These experiences helped me acquire many organizational and human skills : English Teacher | ANACOURS | Paris, Elancourt - France (2015-2016) Private English lessons for high-school students. ➤ Pedagogy ➤ Planning ➤ Tracking Receptionist & General Services Officer | SWAROVSKI International | Paris - France (Summer 2016) Reception, inventory management, bookings in French and English. ➤ Organization ➤ Teamwork Certificated Animator | Malakoff Médéric & day care centers | Saint-Quentin-en-Yvelines, Elancourt - France (Summers 2011 - 2014) Responsibility of children (4-12yo), development of activities, various administrative tasks. ➤ Leadership & Team management ➤ Pedagogy & Education ➤ Planning ➤ Creativity Show less