𝗧𝗿𝗮𝗻𝘀𝗶𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗜𝗻𝘁𝗲𝗴𝗿𝗮𝘁𝗶𝗼𝗻 𝗥𝗼𝗹𝗲𝘀:- 𝗔𝗰𝘁𝗼𝗿 𝗶𝗻 𝗧𝗿𝗮𝗻𝘀𝗶𝘁𝗶𝗼𝗻: Transitioning predictive systems from 42Matters to be integrated into Similarweb's future products, ensuring seamless integration and continuity.- 𝗦𝘆𝘀𝘁𝗲𝗺 𝗠𝗮𝗶𝗻𝘁𝗲𝗻𝗮𝗻𝗰𝗲 𝗮𝗻𝗱 𝗘𝗺𝗽𝗼𝘄𝗲𝗿𝗺𝗲𝗻𝘁: Post-acquisition, responsible for maintaining and teaching existing systems to the wider teams at Similarweb, while re-implementing and enhancing their current systems to leverage advanced predictive capabilities.

𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝗰𝗲 𝗧𝗲𝗮𝗺: Led and developed the data science team, empowering and mentoring members and growing with them. Spearheaded project formulation and execution, ensuring successful machine learning model deployment and timely delivery.𝗥𝗼𝗹𝗲 𝗮𝗻𝗱 𝗥𝗲𝘀𝗽𝗼𝗻𝘀𝗶𝗯𝗶𝗹𝗶𝘁𝗶𝗲𝘀:𝗔𝗽𝗽 𝗖𝗮𝘁𝗲𝗴𝗼𝗿𝗶𝘇𝗮𝘁𝗶𝗼𝗻: Developed an advanced IAB classification system leveraging text embedding, cosine similarity, and Amazon Mechanical Turk. This initiative doubled the coverage of the previous system and increased accuracy by 25%, significantly improving ad targeting and blacklist detection.𝗥𝗲𝘃𝗲𝗻𝘂𝗲 𝗘𝘀𝘁𝗶𝗺𝗮𝘁𝗶𝗼𝗻: Created sophisticated models to estimate app earnings, enabling customers to pinpoint high-engagement apps. This provided actionable insights for better-targeted marketing strategies and informed business decisions.𝗔𝗽𝗽 𝗠𝗮𝘁𝗰𝗵𝗶𝗻𝗴: Engineered a graph-based system using Spark and computer vision for efficient cross-marketplace app matching. This solution facilitated accurate comparisons and integrations across different app marketplaces.𝗗𝗲𝗺𝗼𝗴𝗿𝗮𝗽𝗵𝗶𝗰𝘀 𝗘𝘀𝘁𝗶𝗺𝗮𝘁𝗶𝗼𝗻: Implemented demographic estimation through computer vision and Spark, offering clients detailed user profile insights. This enhanced the ability to conduct targeted marketing campaigns based on age and demographic data.𝗞𝗲𝘆 𝗔𝗰𝗵𝗶𝗲𝘃𝗲𝗺𝗲𝗻𝘁𝘀:Successfully led the team to develop and maintain four daily-operational products.Increased the efficiency and accuracy of app categorization and revenue estimation systems.Enhanced client satisfaction by providing detailed and actionable insights into app user profiles.𝗦𝘁𝗮𝗸𝗲𝗵𝗼𝗹𝗱𝗲𝗿 𝗖𝗼𝗹𝗹𝗮𝗯𝗼𝗿𝗮𝘁𝗶𝗼𝗻:Worked closely with stakeholders to define and develop new products, ensuring alignment with business objectives and customer needs.

𝗔𝗱𝗱𝗲𝗱 𝘀𝘂𝗽𝗽𝗼𝗿𝘁 𝗳𝗼𝗿 𝗮𝗱𝗱𝗶𝘁𝗶𝗼𝗻𝗮𝗹 𝗳𝗶𝗹𝗲 𝗳𝗼𝗿𝗺𝗮𝘁𝘀 for geological data to be read from Imaris, the world’s leading Microscopy Image Analysis software.𝗖𝗿𝗲𝗮𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗜𝗺𝗽𝗹𝗲𝗺𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝗼𝗳 𝗮 𝗻𝗲𝘄 𝗱𝗮𝘁𝗮 𝗴𝗮𝘁𝗵𝗲𝗿𝗶𝗻𝗴 𝗺𝗲𝘁𝗵𝗼𝗱𝗼𝗹𝗼𝗴𝘆 for the Imaris platform to get more insights on user behavior.𝗟𝗲𝗳𝘁 𝘁𝗵𝗲 𝗰𝗼𝗺𝗽𝗮𝗻𝘆 𝗱𝘂𝗲 𝘁𝗼 𝗮 𝗹𝗮𝗰𝗸 𝗼𝗳 𝗳𝗶𝘁 𝗯𝗲𝘁𝘄𝗲𝗲𝗻 𝘁𝗵𝗲 𝘁𝗮𝘀𝗸 𝗽𝗿𝗼𝗽𝗼𝘀𝗲𝗱 𝗮𝗻𝗱 𝗺𝘆 𝘀𝗸𝗶𝗹𝗹𝘀𝗲𝘁 (𝗻𝗼𝘁 𝗶𝗻𝘃𝗼𝗹𝘃𝗶𝗻𝗴 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗮𝗻𝗱 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝗰𝗲)

𝗖𝗿𝗲𝗮𝘁𝗲𝗱 𝗮 𝗡𝗟𝗣 𝗺𝗼𝗱𝗲𝗹 to identify the preferred incentives of the Swiss political class toward some predetermined domains.𝗖𝗿𝗲𝗮𝘁𝗶𝗼𝗻 𝗼𝗳 𝗮 𝘄𝗲𝗯 𝗮𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻 for the study and automatic detection of false watches based on the analysis of their vibration’s signature.𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 𝗼𝗳 𝗼𝗿𝗰𝗵𝗲𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲𝘀 via Airflow to setup Virtual machines and network environment (Terraform) / Slack channels / Github projects / Hour tracking of projects to fully monitor the resources and expenses involved in their development.𝗗𝗲𝘀𝗶𝗴𝗻𝗲𝗱 𝗮𝗻𝗱 𝗜𝗺𝗽𝗹𝗲𝗺𝗲𝗻𝘁𝗲𝗱 the sale and event tracking architecture of a legal company using AWS, Snowflake, and DBT. The implementation aggregates the events generated by the platforms into sessions and users, lowering the costs of processing by a 𝙛𝙖𝙘𝙩𝙤𝙧 𝙤𝙛 5 and producing significant insights for the analyst’s team.

"Monocular 3D vehicle detection with self-attention mechanism" is the thesis that I had the opportunity to perform at the VITA laboratory for transportation. It enabled the detection and localization of vehicles and pedestrians through a monocular RGB camera.This project allowed the development of a new neural network backbone inspired by the Neural language processing field.Grade obtained : 5.75/6

Internship focused on data processing and machine learning to control the qualityof the production processes.Creation of several tools to exploit data from IoT devices and adapt the parameters of the machine in the production lines in real time.The resulting product produced a reduction of the number of stops of approximately 80% while increasing the quality of the end-product.

Teaching Assistant for the Production Management course taught by Amin Kaboli at EPFL.This position consisted in evaluating and delivering the course to students as well as training them to prepare professional presentations on several subjects in an interactive way.

During this internship, my supervisors asked me to implement a human recognition algorithm working on both RGB and Thermal Camera. This algorithm was successfully implemented and is now embedded in the robot's hardware. From the Rovenso team, I keep a really nice experience and I hope that my contribution was proven to be useful for their project

For several years, I have been providing help in mathematics and probability and statistics courses taught at EPFL. The prerogatives to obtain these positions were an average higher than 5.5 / 6 proving a good knowledge of the subject. These positions allowed me to become more pedagogical and to adapt to various situations. My objective is that the course has to be assimilated by the student in a fashion that fits him the most.

Creation of the sponsoring pole for the event Japan Impact. Annual raise of more than 10'000.- of sponsorship and other material goods against services during the event (advertising spots, etc ...).

Help in setting up the sponsoring center at the Lausanne Racing Team and actively looking for sponsors. The project is still looking for funding and allows to promote the development of electric automotive technologies in the university sector.

Three-week apprenticeship to learn the basics of conventional machining (milling, turning, drilling, brazing).