There's a lesson here, and I'm not going to be the one to figure it out.


View My GitHub Profile

My name is Apo and I’m a mighty pirate

Educated in several acronyms across the globe (UNISR, SFI, MIT), I was co-founder and CTO of Tooso, a NLP / IR startup in San Francisco acquired by TSX:CVO.

I led Coveo’s A.I. and MLOps roadmap from scale-up to IPO, and built out Coveo Labs, an applied R&D practice rooted in collaboration (e.g. Stanford, Bocconi, Outerbounds, Farfetch, Microsoft, NVIDIA), open source and open science.

I’m currently a proud NLP advisor for Civic Eagle, and also Adj. Professor of ML at NYU, which is mostly notable because it is the only job I ever had that my parents (sort of) understand.

Where is my mind?

I occasionally share code, ideas and teaching material; if you have no intention of selling me anything, you can also try me on Linkedin.

I talk a lot, and I am often asked to do so in industry (BBC, Walmart, Pinterest, eBay, Farfetch, etc.) and academia (SIRIP, CiE, KDD, Stanford, etc.): popular talks, papers and datasets are highlighted (for the brave reader) at the very end of this page.

I’m building a new company now and I’m always happy to chat about DataOps, MLOps and NLP.

Current stuff

RecList and MLOps “at reasonable scale”

RecList is a testing library for recommender systems: RecList spawned a sponsored open source package, a CIKM competition, and few papers (WWW, Nature Machine Intelligence).

Having built end-to-end systems at garage, scale-up and IPO scale, I had the privilege of making a lot of mistakes. To share my learnings, I introduced the Reasonable Scale ML in “You don’t need a bigger boat” (and related articles).

Current interests: ML testing, developing in the Modern Data Stack.

A.I. research

My recent research is in (mostly) applied and (sometimes) theoretical topics at the intersection of language, learning and retrieval.

I am co-organizer of SIGIR eCom, Industry Sponsorship Chair for CIKM 2022, and I’ve been involved in organizing many NLP events (COLING, ECONLP, ECNLP, EMNLP). My work has been presented in venues such as NAACL, WWW, RecSys and Nature journals: our work on cognitively-inspired query embeddings won the Best Paper Award at NAACL 21.

As a true SFI alumnus, I am an old-fashioned generalist, and I gave small contributions to a bunch of topics outside “traditional A.I.”: archeology, agent-based models, philosophy of mind, political science.

Current interests: multi-modal representations.

Old stuff

In previous lives, I managed to get a Ph.D., work for a professional basketball team, simulate a pre-Columbian civilization and give an academic talk on videogames (among others improbable “achievements”).

Some time before Brad Pitt’s movie, I led one of the first attempts of running sophisticated analytics for a professional basketball team.

I also led the first data analysis and vizualization effort on Milan’s bike-sharing service, which received plenty of press coverage. No bikers (and no bureaucrats) were harmed for the project.

About this page

The content of are released under the BY-NC-ND license; my chibi has been designed by the incredibly talented wisesnail.

Last update: December 2022.


Quick links to selected talks, papers, datasets: if there’s a paper, talk, slide deck you know I have, but you can’t find it (here or elsewhere), please do get in touch directly.

Selected talks

Selected papers


Aside from research and tutorials, our datasets have been successfully used by dozens of master students to defend their thesis at Tillburg University and Politecnico in Milan.