Advanced Systems Engineering Student at Universidad Tecnológica Nacional (UTN)

MY ASPIRATIONAL ROLES:

MLOps Engineer · ML Engineer · Backend Engineer · DevOps

LinkedIn · Portfolio · rubiovalentin.work@gmail.com

I am an advanced Systems Engineering student at Universidad Tecnológica Nacional (UTN), focused on building production-oriented machine learning systems, backend APIs, data pipelines, and cloud-native infrastructure.

My main professional goal is to grow as an MLOps Engineer, while also fitting naturally into roles such as ML Engineer, DevOps, and Backend Engineer. I enjoy working at the intersection of software engineering, machine learning, automation, monitoring, and scalable backend systems.

I focus on designing clean, maintainable, and testable systems using Python, FastAPI, Django, PostgreSQL, Docker, AWS, MLflow, Prefect, Prometheus, Grafana, Kafka, Airflow, and Clean Code practices.

• MLOps platforms and production-ready ML systems
• ML model serving, monitoring, and drift detection
• Backend APIs with Python, FastAPI, and Django
• Data pipelines and workflow orchestration
• Containerized applications and cloud deployments
• Observability, metrics, and infrastructure automation
• Clean architecture, testing, and software engineering best practices

• SOLID
• DRY
• KISS
• YAGNI
• Clean Architecture
• Service Layer Pattern
• Repository Pattern
• Spec-Driven Development
• Type hints and explicit contracts
• Automated testing
• Container-first development
• Observability

• Systems Engineering
• Calculus
• Linear Algebra
• Statistics fundamentals
• Software architecture
• Databases
• Algorithms and data structures
• Operating systems

Production-oriented MLOps platform for predictive maintenance.

A machine learning platform focused on industrial predictive maintenance, combining model training, API serving, monitoring, drift detection, orchestration, and cloud deployment.

Main technologies: Python, FastAPI, XGBoost, Prefect, MLflow, Docker, AWS ECS, Prometheus, Grafana, pytest.

Highlights:

• ML model serving through FastAPI
• Predictive maintenance pipeline
• Drift detection and monitoring
• Prometheus and Grafana observability
• Dockerized services
• CI/CD and AWS ECS deployment
• Automated testing with pytest

Repository: https://github.com/valerubio7/predmaint-ml-platform

Backend/fullstack academic management platform.

A university academic management system with role-based access control, enrollment workflows, exams, academic records, service-layer business logic, testing, and containerized deployment.

Main technologies: Python, Django, PostgreSQL, Docker, pytest, Railway.

Highlights:

• Django-based backend architecture
• Service layer pattern
• Role-based access control
• PostgreSQL database
• Automated tests with pytest
• Dockerized deployment

Repository: https://github.com/valerubio7/academic-management-system

Real-time MLOps platform for fraud detection.

A fraud detection platform designed around streaming data, machine learning pipelines, feature engineering, model tracking, drift detection, observability, and event-driven architecture.

Main technologies: Python, Kafka, TimescaleDB, Redis, XGBoost, MLflow, Evidently, Airflow, Docker, Prometheus, Grafana.

Highlights:

• Real-time fraud detection architecture
• Kafka-based streaming pipeline
• Feature engineering workflows
• MLflow experiment tracking
• Drift detection with Evidently
• TimescaleDB for time-series data
• Redis-based caching layer
• Observability with Prometheus and Grafana
• Multi-service Docker environment

Repository: https://github.com/valerubio7/fraud-detection-system