Juan Elenter

Bio

> I'm a Research Scientist at Spotify, working on pretraining and finetuning foundation models for large-scale personalized systems. My current focus is on LLM-based recommenders, integrating catalog knowledge via semantic IDs and modeling long-range user behavior at scale. I have experience building efficient training pipelines and running rigorous offline and online evaluations.

Before graduate school, I worked on genomic motif discovery through ATAC-seq analysis at Stanford's KundajeLab. I also interned at CERN , contributing to the CMS Open Data initiative alongside Dr. Lassila-Perini.

I'm originally from the beautiful city of Montevideo, Uruguay, where I studied at Universidad de la República. During that time, I played for Uruguay’s national water polo team while also working as a software developer at IBM. If any of that resonates with you — or if you'd like to share some mate — feel free to reach out.

My work

Broadly, I develop learning systems that scale efficiently with data and compute. At Spotify, I apply these methodologies to large-scale recommendation systems, focusing on sequential generative modeling and integrating LLMs into high-performance recommendation stacks.

Throughout my graduate studies, I adopted a data-centric perspective of ML, focusing on continual model fine-tuning as new, diverse data emerges. This has driven my work in active and continual learning using large pre-trained models. On the theoretical side, my work on duality-based constrained optimization has shown that dual subgradient methods can yield near-optimal and near-feasible solutions, without randomization, despite non-convexity. This allows models to not only excel at their main task, but also meet critical requirements such as robustness and fairness.

I also have a particular interest in problems involving biological signals such as genome sequences, medical images and the gut microbiome.

Projects

ATAC-seq analysis and motif discovery
@ Stanford, KundajeLab

Prediction of complex traits in agriculture.
@ UdelaR, FarielBerry Lab
I find this case very confusing, and have not thoroughly checked the result. R.A.Fisher

CMS Open Data Initiative
@ CERN, CMS

Vitæ

• Spotify 2024-Present

  Research Scientist
  Personalization - Generative Recommendaton
• Simons Foundation 2022

  Summer Intern
  Center for Computational Mathematics
• University of Pennsylvania 2021-2024

  The Wharton School & SEAS
  MA in Statistics
  MEng in Electrical and Systems Engineering
• Stanford University 2021

  Visiting Student at KundajeLab
  ATAC-seq analysis, motif discovery
• CERN 2020

  Intern
  CMS Open Data initiative
• IBM 2019

  Full Stack Developer
  
• Universidad de la República 2016-2021

  Bsc. Electrical Engineering
  Signal Processing