He was then a researcher at the Max Planck Institute in Tuebingen, working on Machine Learning and in particular Statistical Learning Theory and Kernel Methods. In 2004 he joined a startup company where he lead a research team and developed ML software for predicting manufacturing quality. Olivier joined Google Zurich in 2007 and contributed to many aspects of the search engine, in particular leading an engineering team working on Language Understanding and the Knowledge Graph. In 2016, he joined the Research team and is now working on Deep Learning and Language Understanding, leading the Brain teams in Zurich and Paris. His research interests include Learning with limited supervision (Semi-supervised or Unsupervised), AutoML (automation of Deep Learning), Learning of world representations and world knowledge.