Data Scientist

About Mirakl

Mirakl is the leader in software solutions for e-commerce. We offer companies a unique suite of solutions that enable them to significantly transform their digital business to accelerate sustainable and profitable growth. Since 2012, Mirakl has been supporting B2C and B2B companies with the most advanced, secure, and scalable technology, enabling them to digitize their business and expand their offering through marketplaces or dropshipping, facilitate the management of their suppliers' catalogs and payments for greater efficiency, offer a personalized shopping experience to their customers, and increase their profits through retail media. Mirakl is the partner of choice for over 450 leading companies worldwide, including Airbus, Maisons du Monde, Decathlon, H&M, Sonepar, and Toyota Material Handling.

Our technical and product teams, named Mirakl Labs, are mainly spread across our 2 hubs in Paris and Bordeaux. They collaborate daily to address the challenges of our clients and users by responding to various challenges related to new features, scalability, security, and ergonomics. They operate in agile mode and are organized into Squads composed of a Squad Lead, 5 developers, a Product Manager, and a QA. Each Squad specializes in a functional scope to design and implement new features, their evolutions, and APIs (with a micro-services breakdown). All teams are responsible for their scope, and each employee contributes their experience and ideas. Innovation, feedback, and involvement in decision-making are at the heart of our philosophy.

About the Job

Integrated into our Data Science team, your main mission will be to prototype, iterate, and deploy algorithms in collaboration with the Product teams, Data Engineers, and development teams. Your projects will focus on Marketplace catalog challenges, including NLP, Computer Vision, and the large-scale use of Generative AI (custom LLMs).

Catalog Topics:

• Automatic rewriting of Marketing content based on business needs
• Extraction of product attributes from images and free text
• Detection of variant products
• Product categorization
• Automatic seller product onboarding
• Merging product sheets from multiple sources
• Trend prediction for products

What's in it for you?

• Implement algorithms that will have a visible impact on over 500 e-commerce sites/marketplaces in 40 countries, some with very significant volumes (millions of products, customers, orders per year).
• Varied cutting-edge techniques (multimodal models, LLM fine-tuning, etc.).
• Real autonomy and responsibility in projects for which you have ownership.

Our Stack and Tools

Python, Tensorflow, Pytorch, Hugging Face, Databricks, Spark, AWS (Amazon Redshift, s3, etc.), SQL, Airflow, Delta Lake.

Day-to-day

• Analyze, prepare data, prototype algorithms
• Deploy them in collaboration with Data Engineers and development teams
• Create dashboards to illustrate algorithm relevance and monitor production
• Present results in weekly data science meetings and participate in team brainstorming sessions
• Exchange with other teams to refine use cases, user experience, and integration methods

You'll love this job if

• You have a minimum of 4 years of experience as a Data Scientist, with significant experience in NLP and applied ML in a business context.
• You have already deployed Machine Learning algorithms into production.
• You have a good knowledge of NLP and Computer Vision algorithms and State-Of-the-Art architectures.
• You have experience in Spark development.
• You are pragmatic, data-driven, and business-oriented.
• You enjoy owning your subjects and are autonomous with a great team spirit.