System Architect & AI Infrastructure Engineer. Agent systems architecture, foundation model design (custom JEPA Transformer Encoder–World Model), distributed ML platforms. Fulbright–García Robles Scholar. NYU M.S. Data Science, UNAM B.Eng. + B.Sc.
System architect and AI infrastructure engineer. Lead scientist on a custom JEPA Transformer Encoder–World Model architecture for market panel data, and defines system architecture, technical direction, and infrastructure standards for agent systems and the surrounding foundation model platform at Kuona, providing architectural guidance across engineering and data science teams.
Track record of replacing fragmented, per-client systems with generalized platforms that compound over time — in agent execution, distributed ML training (500+ servers), and forecasting infrastructure. Architectures defined for two major product lines have become organizational standards followed across teams. Fulbright–García Robles Scholar; M.S. Data Science from NYU; dual degrees from UNAM.
Multi-agent analytical platform for autonomous analysis over tabular data. 90% task success rate; reduces cross-silo analytical queries from hours to minutes. Used by global retailers and manufacturers across 5 database backends.
Custom JEPA Transformer Encoder–World Model architecture — an energy-based, joint-embedding predictive model designed from the ground up for market panel data. Learns compact representations of unobservable market dynamics and is the single foundation underlying all forecasting, intervention simulation, and causal probing tasks across the platform. Lead scientist on the architecture itself and on its training objective; the surrounding infrastructure supports immediate inference via modular per-client adapters without retraining.
Knowledge graph engine giving LLMs structured memory over heterogeneous documents. Sub-second federated retrieval, ~95% recall, significant token consumption reduction.
Natural-language-to-SQL engine across five database backends. ~95% SQL generation accuracy, sub-minute cross-source query generation.
Multi-agent entity resolution across all company entity systems — products, geographies, promotions, brands, ontological concepts. 10–20 seconds including disambiguation. Read more
Agent-driven data visualization that autonomously selects chart types, maps visual encodings, and renders interactive charts. Eliminates manual BI configuration for non-technical users.
Autonomous evaluation harness driving multi-turn agent sessions end-to-end. CI-integrated regression detection for failure modes invisible in single-turn testing.
Unified distributed ML training platform replacing fragmented per-client systems. 500+ servers, thousands of model training jobs weekly. Pre-modeling data governance checks catch data errors upstream, saving hundreds of GPU hours in wasted training.
Custom task orchestration system for heterogeneous distributed computing with arbitrary horizontal scalability and a UNIX-like process control interface for remote task management.
Time series forecasting library with transparent multi-horizon predictions, automatic hyperparameter search, and native ensemble model support.
Python library for creating good-looking reports programmatically without templates or complex layout systems. Automatically transforms Python objects (Matplotlib figures, Pandas DataFrames) into HTML using Bootstrap 5's grid for layout. MIT licensed. GitHub
Led a multidisciplinary group that built a Julia language replacement for the AIMPAC software suite for describing the quantum structure of molecules. Parallel, GPU-ready replacement for the original Fortran code. Collaboration between UNAM's IIMAS and School of Chemistry. View project
Parallel implementation for supply chain optimization on Nvidia GPUs using CUDA and Julia. Binary particle swarm optimization algorithm with conservation-of-flow constraints and LP-based cost evaluation. View project
Improved upon previous results in predicting future academic collaborations using topological data. Created a reduced feature vector via SVD on the collaboration network's adjacency matrix, improving on Hasan et al. (2006). View project
Fulbright Scholar from Mexico to the USA. Multicultural background reflected in daily working fluency across languages and professional contexts.