I lead the AI team at Onfido. We use computer vision and machine learning for online identity verification. From 2015 to 2021, I was leading the machine learning team for recommendation at Criteo, where we transformed the recommendation engine using a lightweight encoder-decoder architecture. From 2010 to 2014, I was leading the computer vision team at Thales Optronics in France. I graduated with a PhD in robotics/computer vision in 2010, under the supervision of Prof. Seth Teller. I was a core member the MIT team at the DARPA Urban Challenge in 2007. My work was published at CVPR, ICCV, ICRA and IJFR. I am a reviewer for NeurIPS, ICML and ICLR.

Blog

• Dec 2022, Building a recommendation engine from scratch
• Sept 2022, Where self-driving is headed
• Jan 2022, Lightweight Representation Learning For Efficient And Scalable Recommendation
• Dec 2021, The high road of performance review
• May 2020, The tradeoffs of large-scale machine learning: the price of time
• Feb 2020, Your first 90 days as a tech lead
• June 2019, Making your company machine learning-centric

also on Medium

Featured talks

• 2020, Job interview talk at Onfido, Scalable representation learning and retrieval for online advertising
• 2018, 7th RecSys London Meetup, Acquisition: Recommending Products From a Retailer That the User Never Visited Before
• 2017, Criteo RecSys London, Product recommendation beyond collaborative filtering, welcome to the twilight zone!
• 2016, ICML: Online Advertising Systems Workshop, New challenges for scalable machine learning in online advertising
• Oct 2014, ICIP, Image and Video Processing for Defense, Transportation, Homeland Security, and Observation from Space: Industrial Expectations and Technological Challenges

Publications

• Lightweight representation learning for efficient and scalable recommendation, arxiv:2101.00870v2, Nov 2021
• Ground robot navigation using uncalibrated cameras, ICRA 2010
• Body-relative navigation guidance using uncalibrated cameras, ICCV 2009
• A perception-driven autonomous urban vehicle, IJFR 2008
• Wide-area egomotion estimation from known 3d structure, CVPR 2007
• SLYK: A Transparent Fault-Tolerant Migration Platform, MIT Technical Report, 2005
• The City Scanning Project: Validation and Algorithms, MIT Technical Report, 2002

also on Google scholar

Misc.

• In 2019, I taught at M2 level at Paris Dauphine University with Criteo, IASD
• I co-founded Reveal, the RecSys workshop for causal recommendation with Microsoft, Netflix and Cornell University. The workshop ran from 2018 to 2020 and now continues as the Consequences workshop.
• Here is a list of book recommendations for tech leaders.