
Introducing AppChecker: The Guardian of Software Quality at Criteo
In a world where distributed systems have become the norm and development cycles are accelerating, software quality can no longer be left to chance: it must be measured, verified, and integrated into the daily work of teams. At Criteo, this requirement is even more critical because services are numerous, interdependent, and essential to the proper…

How RecSys & LLMs Will Converge: Architecture of Hybrid RecoAgents
Recommender systems have become critical infrastructure in commerce. Their role is not only to surface relevant items but also to shape how users explore, compare, and decide. Improvements in recommendation translate directly into superior business outcomes: higher engagement, more conversions, stronger loyalty, and more efficient allocation of marketing budgets. Over the last couple of years,…

Agents, APIs, and Advertising: Lessons From Engineering Our MCP Server
MCP, Model Context Protocol, has made quite some noise in the past year as it promises a simpler, user-driven, integration of tools into Large Language Models (LLMs). At Criteo, we believe that MCP will be key to empowering our clients and giving them the control to create and manage advertising campaigns in a new way:…

Building an Internal Developer Portal: Insights from the Journey So Far
Learn how Criteo built an Internal Developer Platform with Backstage, a dedicated team, shared ownership, and workflows designed to improve developer experience.

Why And How We Organize Coding Dojos
If you are looking for a way to both have fun and improve your coding skills (or those of your team), I have some good news: we have open-sourced a repo that contains material to organize coding dojos! 🎉 👇 GitHub – criteo/coding-dojo: Some content to organize some coding dojos Some content to organize some…

Importance of Graceful Shutdown in Kubernetes
Have you ever deployed a new version of your app in Kubernetes and noticed errors briefly spiking during rollout? Many teams do not even realize this is happening, especially if they are not closely monitoring their error rates during deployments. There is a common misconception in the Kubernetes world that bothers me. The official Kubernetes…

Enhancing Service Reliability with Feature-Based SLOs: A Comprehensive Approach
In recent years, our focus has been on defining Service Level Objectives (SLOs) for HTTP API endpoints. While this approach has proven beneficial for development teams, it has also had less impact on external customers and product teams. Users typically expect SLOs to be associated with features rather than individual endpoints or services. Communicating the…

Research Card: FairJob – A Real-World Dataset for Fairness in Online Systems
Research Card on how to make the outcome prediction in online systems fairer? Title: FairJob: A Real-World Dataset for Fairness in Online Systems Short Title: Discover and mitigate bias in advertising Authors: Mariia Vladimirova (Criteo AI Lab), Federico Pavone (Paris-Dauphine), Eustache Diemert (Criteo AI Lab) Team: Research.FDL, collaboration with Paris-Dauphine University Revue: NeurIPS 2024, datasets and…

Research Card: Fixed Point Label Attribution for Real-Time Bidding
Research Card on how to attribute positive outcomes to touchpoints in a sequence of displays leading to a conversion. Paper: Fixed Point Label Attribution for Real-Time BiddingAuthors: Martin Bompaire, Antoine Désir, Benjamin HeymannCategory: Operations ResearchRevue: Manufacturing and Service Operations Management Why did we work on this topic (the problem we want to solve)? In display advertising,…

Transitioning to a Career in Code (Women Who Code talk)
We spend so much time in our jobs. Society evolved to put work at the center of everything. We dedicate at least eight hours of our day, five days a week, to work. We need to choose our major when we are 18 years old. Sometimes people are lucky and find their call right away;…










