We could talk about the fact that we are making display perform better. And this is what we do right here. But the exciting part for us engineers is how we are doing this, really. Our technology takes an algorithmic approach to determining what user we show an ad to, when, and for what products. For billions of unique adverts that are created and displayed at lightning fast speeds every day.
Here are a few figures, because we like data, yes indeed we do:
- 15 datacenters (8 with computing capacity + 7 dedicated to network connectivity) across US, EU, APAC
- More than 20000 servers and over 50 PiB of storage on our HPC cluster
- Over 100B HTTP requests and close to 4B unique banners displayed per day
- Respond to bids in 80ms or less, 24/7
- Peak 3M http requests per second
- Less than 10ms on average to select optimal campaign
- 10 ms to find best product in catalogue of hundreds of millions of products
- Tens of TB of new data stored daily
- Close to 4PB of data read daily
- Over 100 PiB of raw storage
- Largest public Machine Learning Dataset in the world with over 4 billion lines and over 1TB in size
- Technologies: Hadoop, Couchbase, Redis, Mesos, Kafka, Storm, Cassandra, Spark, Vertica, Druid, …
The R&D department develops the infrastructure and tools that allow us to manage these ever increasing volumes of data. More advertisers supplying more catalogues of products, more publishers and more user variables mean that we are working in a very fast-paced release cycle and are adding new capabilities weekly and even daily.
The 470 engineers@criteo are building the next generation of digital advertising technologies that allow us to manage billions of ad impressions, each one personalised automatically for its audience. This is truly big data and machine learning without the buzzwords! We have one of the best engineering teams in Europe, and our values are getting stuff done and having fun.