Barrie, Ontario, Canada

Felipe Alfonso

Software Engineer — Backend, Data Pipelines & Applied ML

Software engineer with 5+ years of experience across backend development, large-scale data pipelines, and applied machine learning. I've built systems that process millions of records a month, trained NLP/LLM pipelines on distributed GPU infrastructure, and shipped full-stack products end to end — from database schema to deployed UI. Comfortable owning a problem from requirements through production.

Felipe Alfonso
10M+
transactions analyzed for anomalies
1,145+
production crawler releases shipped
50%
faster deployments via CI/CD automation
20+
engineers mentored and onboarded

About

Software engineer with 5+ years of experience across backend development, large-scale data pipelines, and applied machine learning. I've built systems that process millions of records a month, trained NLP/LLM pipelines on distributed GPU infrastructure, and shipped full-stack products end to end — from database schema to deployed UI. Comfortable owning a problem from requirements through production.

Featured Projects

Personal, non-confidential builds — shown in full, screenshots included.

🔒 Mercado Libre Work (Confidential)

Three and a half years building data engineering and applied ML systems at Mercado Libre. Described here only in aggregate, high-level terms — no internal code, architecture, or data is shown.

Competitive Intelligence Crawling Platform

Queue-driven engine crawling competitor retailers at e-commerce scale.

An orchestration engine that scheduled crawling jobs multiple times a day across dozens of competitor retailers, built on a plugin-based scraping SDK that became the shared foundation for every downstream competitive-intelligence service. Event/queue-driven and horizontally scaled, with years of continuous, incremental production operation.

  • 1,145+ production releases of the crawl orchestration engine
  • Plugin architecture (search, product, seller, pricing) reused across every retailer integration
  • Human-in-the-loop review tooling to keep automated matches accurate at scale
Python Node.js Docker Message Queues Async I/O

🔒 Built for Mercado Libre — described at a high level only; implementation details are confidential.

Financial Anomaly Detection Engine

Clustering, autoencoders, and classical statistics over 700+ engineered features.

A data-quality-governance pipeline for financial transaction data, combining clustering, an autoencoder, and classical statistical techniques to flag outliers across millions of transactions. Fed real-time alerting and executive BI dashboards, replacing manual review with automated, continuous checks.

  • 700+ engineered time-series features driving the anomaly-detection models
  • Processed 10M+ transactional records to identify and flag outliers
  • Automated schema validation for hundreds of datasets across dozens of business units
Python Jupyter Poetry CI/CD

🔒 Built for Mercado Libre — described at a high level only; implementation details are confidential.

NLP Transaction Classifier

Text classification for miscategorized Open Banking transactions.

An NLP model that classified transactions left in a catch-all 'uncategorized' bucket, using text normalization, TF-IDF vectorization, and class-imbalance handling to make sense of messy, real-world financial text. Iterated from proof-of-concept through to a near-production release.

  • Tackled real-world class imbalance in transaction-category data
  • Iterated the same model across three stages: research, onboarding, and production hardening
  • Directly supported Open Banking / Open Finance compliance reporting
Python scikit-learn NLP Jupyter

🔒 Built for Mercado Libre — described at a high level only; implementation details are confidential.

End-to-End MLOps Pipeline

ETL → training → model-serving, with a sensitive-data governance layer.

A complete MLOps pipeline for a spending-behavior propensity model: data extraction and transformation, training, and model-serving, composed with Hydra configuration management and a dedicated module for handling regulated, sensitive data safely throughout the lifecycle.

  • Full lifecycle ownership: ETL, training, and model-serving in one production pipeline
  • Dedicated sensitive-data governance module for regulated financial data
  • BDD-style system tests validating behavior end to end
Python scikit-learn BigQuery Hydra pytest (BDD)

🔒 Built for Mercado Libre — described at a high level only; implementation details are confidential.

Experience

Data Systems Agent (Operations Engineering & Systems Lead)

Jun 2024 – Jul 2026

FedEx Express Canada · Barrie, ON

  • Built Python automation tools integrating the Anthropic API and Claude for daily production workflow acceleration and decision support.
  • Applied prompt engineering and AI-assisted development practices to operational data processing and reporting tasks.

Systems Analyst (Co-op)

Jan 2025 – Apr 2025

Financial Services Regulatory Authority of Ontario (FSRA) · Toronto, ON

  • Resolved performance-impacting bugs in UAT/PSP platforms used for regulatory review.
  • Designed and implemented ETL pipelines to streamline data workflows for the Pensions Database.
  • Partnered with cross-functional teams on functional specs, testing, and deployment.

Data Science Software Engineer

Jan 2021 – Jun 2024

Mercado Libre · Colombia (remote)

  • Built machine learning training pipelines for large language models, focused on NLP tasks, collaborating directly with ML researchers to align workloads to distributed GPU infrastructure.
  • Designed large-scale web data collection systems to source alternative data for model training, improving dataset diversity and accuracy.
  • Engineered ETL pipelines moving data into cloud storage, processing on the order of 10M+ records and improving downstream read/re-read efficiency.
  • Led data quality and anomaly-detection initiatives across multiple business units, improving data reliability by roughly 30% and enabling automated schema validation for hundreds of datasets.
  • Wrote event-driven, multi-process Python services to keep front-end-facing systems responsive under load, and investigated production issues across the stack.
  • Mentored and onboarded 20+ engineers and data scientists into internal tooling and practices.

Junior Developer

Jan 2020 – Dec 2020

Robotec Corporation · Bogotá, Colombia

  • Built a security-camera monitoring application integrating in-house and third-party software.
  • Implemented motion-camera control via the ONVIF protocol and integrated it into the main desktop app.
  • Authored technical and user documentation for the deployed system.

Skills

Languages

  • Python
  • TypeScript / JavaScript
  • SQL
  • C#
  • PHP

Backend & APIs

  • FastAPI
  • Node.js / Express
  • .NET Core
  • REST APIs
  • GraphQL
  • Microservices
  • Event-driven architecture
  • Multi-threading / multi-process design

Data & Machine Learning

  • ETL pipeline design
  • Large-scale web data collection
  • BigQuery
  • Anomaly detection & data quality frameworks
  • ML training pipelines (NLP / LLM)
  • Distributed computing across GPU clusters

Databases

  • PostgreSQL
  • MySQL
  • Microsoft SQL Server
  • MongoDB

Frontend

  • Next.js / React
  • Tailwind CSS
  • HTML / CSS
  • Handlebars

Platform & Practices

  • Docker
  • CI/CD
  • Git
  • Agile
  • Linux
  • Automated testing

What's Next: Agentic AI

I'm currently exploring how to apply the same production-engineering discipline — testing, observability, clean architecture — to LLM agents. This section will grow as those projects ship.

In progress

Multi-step agent workflows

Agents that plan, call tools, check their own work, and recover from failure instead of one-shot prompting.

Exploring

Retrieval-augmented generation

Grounding LLM responses in private/internal knowledge bases instead of relying on parametric memory alone.

Exploring

Structured tool use

Function-calling and structured outputs wired into real, production-shaped APIs — not just demos.

Contact

Open to backend, data engineering, and applied ML roles. Reach out any time.