Skip to content
View exemartinez's full-sized avatar
5 followers · 11 following

Achievements

Achievement: YOLOAchievement: Arctic Code Vault Contributor

Achievements

Achievement: YOLOAchievement: Arctic Code Vault Contributor

Block or report exemartinez

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
exemartinez/README.md

Ezequiel H. Martinez

Data & AI Systems Architect · Buenos Aires, Argentina

From lakehouse design and orchestrated pipelines to LLM-powered agents and RAG — built end-to-end by someone who also does the data science behind them.

What I build

  • Data Platforms — cloud-native lakehouses (Snowflake, BigQuery, DBT, Airflow/Prefect), end-to-end from ingestion to serving. Production scale: 13TB+, 700+ pipelines, 60+ sources.
  • AI / LLM Systems — RAG pipelines, agent-based automation, LLM-powered document processing. Recent: HR/payroll resolution agents, workforce planning systems.
  • ML & Fraud Detection — Isolation Forest, AWS Fraud Detector, custom statistical models over high-volume transaction data (1B+ monthly transactions).
  • Data Engineering — ETL/ELT at scale, CDC pipelines, Kubernetes-based distributed processing, API integrations across SaaS ecosystems.

Stack I work with daily

Data:       Snowflake · DBT · Airflow · Prefect · Kafka · Spark · Airbyte
AI/LLM:     LangChain · ChromaDB · RAG · Agents · OpenAI · Claude · Ollama
Cloud:      AWS (EMR, ECS, ECR, Lambda, SQS, RDS) · GCP
Languages:  Python · SQL · Scala · Bash
Infra:      Docker · Kubernetes · Terraform · CI/CD

About this profile

Most of my production work lives in private repositories under NDA — the public repos here are personal experiments, tooling, and academic work.

Current public projects include a structured data extraction tool for Argentine bank statements (simple_santander_rio_parser) and ML research from my Master's in Data Science at ITBA (gravitational_waves_classifiers).

Background

25+ years building data and software systems across fintech, agro, retail, and pharma.
MSc Data Science · MBA · BSc Computer Science.
Previously: Worky · Cobre · Microsoft · Deloitte · Cognizant.

📎 LinkedIn · 📧 exemartinez.info@gmail.com

Pinned Loading

  1. simple_santander_rio_parser simple_santander_rio_parser Public

    Extracts and normalizes transaction data from Santander Río PDF statements into structured CSV — Python-based ETL for personal financial analysis.

    Python 1

  2. gravitational_waves_classifiers gravitational_waves_classifiers Public

    ML classification of gravitational wave signals using SVMs and RNNs. Final project for MSc in Data Science at ITBA — built with Python, Keras, and Scikit-Learn.

    Python 1

  3. Contact_Manager_Messager Contact_Manager_Messager Public

    Automation tool that ingests LinkedIn contact exports and sends personalized outreach emails from a single template. Python, CSV processing, SMTP.

    Python 2

  4. solpatagonico solpatagonico Public

    Full-stack reservation and inventory management system for hospitality businesses. PHP/MySQL, built as a complete operational web application.

    PHP 2

  5. ExperienciaQuilmes ExperienciaQuilmes Public

    AngularJS prototype built for the Eklos Hackathon Buenos Aires — top 5 finalist. Consumer experience concept for Quilmes Challenge.

    HTML 1

  6. harvestor harvestor Public

    Java library for Twitter network growth — models follower graph traversal and targeting logic. Early exploration of social graph data structures.

    Java