Víctor G. G. Quiroga

Delivered enterprise AI and data solutions for airline and retail clients, including GateGroup and Grupo AXO (Calvin Klein).

• Architected Azure-based data pipelines and automation workflows for enterprise operations, improving SLA reliability and reducing manual work.
• Implemented enterprise data governance and cataloging workflows using Microsoft Purview across SAP and distributed systems.
• Designed and deployed an LLM-powered retail intelligence system for Grupo AXO (Calvin Klein), integrating multimodal data from store visits, promoter activity, inventory, events, and images.
• Reduced visual merchandising photo reporting workflows from hours to seconds through AI-driven automation.
• Built inventory reconciliation and anomaly detection pipelines, reducing shrinkage by 20% and identifying root causes such as theft, inventory mismatch, and missing labels.
• Developed demand forecasting and trend detection models across products, colors, stores, and regional hot/warm/cold zones, reducing analysis time from days to seconds.
• Enabled natural language interaction with analytics and AI workflows through a WhatsApp interface for non-technical business users.

Worked across enterprise data, cloud automation, and AI experimentation initiatives for clients including Toyota, Boehringer Ingelheim, and Nestlé.

• Designed and automated infrastructure workflows across 1,500+ cloud resources using AWS, Terraform, and serverless architectures.
• Improved IT governance efficiency by 30% through automated tagging across 2,000+ AWS assets.
• Built automated deployment workflows for Python OCR pipelines using GitHub Pipelines, Serverless, and CloudFormation.
• Implemented secure data pipeline components and encryption middleware for enterprise supply chain data platforms.
• Resolved 11 high-to-critical security issues across production and non-production cloud environments.
• Contributed to AI-driven experimentation pipelines in Deloitte's Azure Hackathon, helping achieve 20x acceleration in R&D simulations using Azure Quantum ML.

Built data, ML, and compliance systems in a high-growth fintech environment.

• Designed high-throughput decision systems with theoretical scaling up to 10,000 transactions per second using PySpark ML and microservices.
• Prevented a potential 20x portfolio loss by combining LSTM forecasting, Monte Carlo simulation, statistical modeling, and inventive feature engineering under constrained tooling conditions.
• Produced reproducible modeling outputs and technical evidence for regulatory validation in a pre-LLM tooling environment.
• Automated regulatory reporting workflows covering 19 CNBV reports by coordinating cross-functional engineering and data teams.
• Built data quality and schema inference frameworks and helped recover 99.98% of customer data during a production outage incident.

Worked on enterprise data governance, customer intelligence, and predictive modeling initiatives.

• Productionized CRM intelligence data models using PySpark, enabling compatibility with enterprise marketing automation workflows in 3 months.
• Developed alternative credit scoring models using non-traditional data sources such as behavioral and web-derived signals, applying feature engineering and machine learning techniques.
• Built scalable data pipelines supporting customer intelligence and enterprise analytics use cases.
• Co-led a semifinalist team in Indra's 2020 DataHack, developing a portfolio rationalization solution using clustering, PySpark, and Azure-based analytics infrastructure.

Machine learning-based signal system for leveraged intraday trading.

• Built a trading system using Lorentzian classification and multi-indicator strategies for 2-minute to 15-minute timeframes.
• Achieved 62.5% profitability in high-frequency trading scenarios.
• Combined statistical and ML-driven signal generation using StochRSI, Williams %R, ADX, and VZO-inspired strategies.

Top-performing team among roughly 100 global teams. Delivered an Azure Quantum ML solution achieving 20x acceleration in R&D simulations.

Built a semifinalist portfolio optimization system using clustering, PySpark, and Azure-based analytics infrastructure.

Ranked top 10% globally, with peak placement in the top 6%, using an ML-based trading signal system.

Ranked 3rd among 150 sustain engineers in enterprise support performance.

Co-authored peer-reviewed research on post-quantum cryptography performance using reproducible statistical analysis and experimental evaluation.

Co-authored peer-reviewed research introducing a trust metric based on survival analysis of cryptographic key interactions.