Buenos Aires, Argentina

Paulo Olveira

Technical Lead, ML/AI

Building production-grade machine learning systems at scale. Taking cutting-edge AI research into real-world infrastructure — from LLM pipelines to multi-objective optimization serving millions of daily predictions.

About

Research to
production,
at scale.

I'm a Technical Lead in ML/AI with deep experience turning state-of-the-art research into systems that hold up under real-world load. My work spans LLM infrastructure, predictive logistics, and the ML platforms that power them.

Currently leading multiple ML/AI teams at MercadoLibre — Latin America's largest e-commerce and fintech platform. I focus equally on rigorous experimentation and the engineering discipline that makes models trustworthy in production.

Pursuing a Licenciatura in Computer Science at UBA alongside industry work. My broader interests include bioinformatics, robotics, and computational neuroscience.

Machine Learning

Deep Learning · Generative AI · LLMs · Predictive Modeling · Multi-objective Optimization

Engineering

Scalable ML Platforms · Online/Batch Prediction · Model Deployment · Observability · ONNX

Frameworks

Python · TensorFlow · PyTorch · XGBoost · LangChain · Hugging Face · OpenAI API

Cloud & MLOps

AWS SageMaker · GCP · MLflow · Kedro · TDD · SOLID · Clean Architecture

Experience

2021 — Present

MercadoLibre

Technical Leader, ML/AI

Leading multiple ML/AI teams within Latin America's largest e-commerce and fintech platform. Architected the migration of legacy prediction infrastructure, significantly reducing latency and operational costs. Led LLM-based item attribute enrichment using prompt versioning, RAG, and context engineering — with custom evaluation frameworks designed for class imbalance and asymmetric error costs. Built multi-objective shipment time prediction maintaining high on-time delivery rates. Mentored cross-functional teams on engineering best practices, accelerating deployment cadence from monthly to weekly automated releases.

LLMs RAG ONNX SageMaker MLflow Team Leadership

2017 — 2021

MercadoLibre

Senior Data Scientist

Core predictive modeling for logistics and delivery operations across MercadoLibre's regional marketplace. Developed high-performance models using TensorFlow, XGBoost, and CatBoost, integrated into production via AWS and SageMaker. Designed dynamic batch/online prediction switching strategies to balance cost and performance at scale, enabling millions of daily predictions.

TensorFlow XGBoost CatBoost AWS Logistics ML

2016 — 2017

Digodat

Analytics Developer

Delivered A/B testing, anomaly detection, and interaction measurement solutions. Built custom data tooling and visualizations to inform business decisions.

A/B Testing Anomaly Detection Analytics

Portfolio

01

Flight KPI Prediction

Predicting airline operational KPIs using least squares regression. An early exploration of applying statistical modeling to real-world logistics data.

02

fadam-microgpt

A pure Python implementation of the FAdam optimizer to replace standard Adam in microGPT, built entirely without PyTorch. It natively reproduces complex mathematical transforms—including a Fisher Information Matrix (FIM) proxy, adaptive matrix-group clipping, clipped natural gradients, and decoupled weight decay.

Coming soon

03

More projects

Additional work in progress — stay tuned.

Research

Conectia 2025 — Contributor

Los desafíos de modelar "¿Cuándo llegará mi pedido?"

A custom PyTorch neural network for probabilistic delivery time prediction using beta distribution parameters and the FAdam optimizer (natural-gradient-aware). Compared against NGBoost as a baseline, the approach achieves substantially faster training and inference, a smaller model footprint, and competitive or superior accuracy — with full ONNX export support for production deployment.

Let's
connect.

Open to collaborations, research conversations, and interesting problems.