Senior Data Scientist - Freelance (3months renewable)

Founded in 2013, Voodoo is a tech company that creates mobile games and apps with a mission to entertain the world. Gathering 800 employees, 7 billion downloads, and over 200 million active users, Voodoo is the #3 mobile publisher worldwide in terms of downloads after Google and Meta. Our portfolio includes chart-topping games like Mob Control and Block Jam, alongside popular apps such as BeReal and Wizz.
The Engineering & Data team builds innovative tech products and platforms to support the impressive growth of their gaming and consumer apps which allow Voodoo to stay at the forefront of the mobile industry.Within the Data team, you’ll join the Ad-Network Team which is an autonomous squad of around 20 people.  The team is composed of top-tier software engineers, infrastructure engineers, data engineers, mobile engineers, and data scientists (among which 3 Kaggle Masters).
The goal of this team is to provide a way for Voodoo to monetize our inventory directly with advertising partners, and relies on advanced technological solutions to optimize advertising in a real-time bidding environment. It is a strategic topic with significant impact on the business.
We're looking for a Senior Data Scientist for a 3 months' contract - potentially renewable with 3 days/week onsite (Paris - Châtelet)

Role

• You will be responsible in designing an end to end image classification product in the context of building new marketing products we would sell to external advertisers.
• You will work in a fast paced environment alongside one of Voodoo Lead data scientist and be supported by Voodoo Data Engineers when necessary.

Profile

• Experience with the industrialisation of the raw data collection (data pipelines)
• Experience building a labelling solution using Vision LLM
• Experience building an evaluation dataset for the solution
• Experience training an image classification model
• Experience analysing the performance to decide feasibility
• Experience iterating on the solution to improve its performance
• Experience industrializing the said model to do inference on millions of images daily
• Experience integrating the said solution to the production systems that will serve it

Our Stack

• Python, Pytorch, Pandas, Airflow, Git, AWS