CV
CV repository
Applied AI technical leadership: production ML, experiment strategy, and academic rigor.
A recruiter-facing overview of impact, experience, and technical depth. Detailed evidence is expandable; the long-form academic record remains available separately.
Profile
Applied AI and Data Science technical leader experienced in production recommendation systems, client-facing AI delivery, experiment strategy, and cross-functional execution. Combines decisive model ownership with roadmap thinking, formal validation, mentoring, a PhD in Astronomy, 30+ Q1 publications, and extensive teaching and supervision experience.
Experience
Mercado Libre · 2024–2026Senior Data Scientist / Machine Learning Engineer
Primary data science owner for a production online ranking model serving recommendations to millions of users in Argentina, Brazil, and Mexico.
- Developed the PyTorch model, features, and embeddings and integrated feature-store data.
- Tripled training-data capacity through Fury pipeline, framework, and CUDA optimization.
- Owned reproducibility and release safety through MLflow, ONNX validation, and a pre-production protocol.
- Designed statistical confidence tools for A/B tests and monitored clicks, purchases, GMV, and model behavior.
- Guided launch, pause, and refinement decisions by communicating evidence, trade-offs, risks, and next steps.
- Partnered across engineering, product, and analytics to deliver measurable conversion lift.
IThreex Global · 2022–2024Lead Data Scientist
Led an eight-person team delivering AI and analytics products in fast-moving, client-facing environments.
- Defined the technical roadmap for the Molibdeno AI platform and created the core Python library for reusable ML workflows.
- Defined OKRs, tracked team execution, mentored and onboarded data scientists, and participated in hiring and evaluation decisions.
- Led tax-revenue forecasting and payment-behavior work as principal technical contact for Kolektor.
- Delivered segmentation and predictive products for retail, tourism, and international-trade clients.
- Built computer-vision models for cattle-weight estimation and a LangChain RAG API.
- Turned business requirements into scoped data products and communicated progress directly to stakeholders.
Universidad Nacional de Córdoba · 2023–presentAssociate Professor
Head of the Data Science course in Applied Mathematics, following twenty years teaching statistics, machine learning, and scientific computing. Supervises graduate researchers and connects formal foundations with implementation.
CONICET · 2004–2023Researcher
Applied Bayesian inference, statistical learning, numerical methods, and HPC to large astronomical datasets. Developed open-source software and automated pipelines in international teams; authored 30+ Q1 papers, supervised researchers, reviewed technical work, and organized academic activities.
Capabilities
Machine learning
PyTorch, Scikit-Learn, XGBoost, ranking, recommender systems, embeddings, feature engineering, computer vision.
Production ML and experimentation
ONNX, MLflow, feature stores, Fury pipelines, CUDA, A/B testing, pre-production validation, Datadog, Looker.
Data, AI, and statistics
Python, SQL, R, NumPy, Pandas, SciPy, BigQuery, Bayesian inference, statistical learning, LangChain, RAG, prompt engineering.
Engineering and cloud
Git, GitHub, Linux, APIs, Sphinx, AWS S3/EC2, GCP BigQuery and Cloud Storage, HPC, reproducible scientific pipelines.
Leadership and domains
Technical direction, roadmap definition, OKRs, mentoring, onboarding, hiring participation, client communication, stakeholder management, and cross-functional delivery in e-commerce, retail, public revenue, tourism, agriculture, and international trade.