Building scalable machine learning platforms, forecasting solutions, and production AI systems.
I'm a Machine Learning Engineer with 5+ years of experience building and deploying scalable AI solutions in production environments.
My expertise spans Machine Learning, MLOps, Data Engineering, and Cloud Infrastructure, with a strong focus on transforming research and business requirements into reliable, production-ready systems.
I hold a M.Sc. in Computer Science from UNICAMP, where my research focused on Explainable AI, Representation Learning, and Human Activity Recognition.
Today, I specialize in designing end-to-end ML platforms, distributed training pipelines, forecasting systems, and modern AI applications.
- 🚀 5+ years building ML systems in production
- ⚡ Reduced large-scale model training time by over 90%
- 📊 Designed forecasting pipelines for thousands of products
- ☁️ Production experience with Azure, Kubernetes, and MLflow
- 🔄 Built scalable batch and real-time ML architectures
- 📚 Published research in Explainable AI and Human Activity Recognition
- 👥 Leading AI initiatives while remaining hands-on with architecture and implementation
- Built distributed forecasting pipelines for thousands of products
- Scalable training architecture using PySpark and Kubernetes
- Automated experimentation and model management with MLflow
- Reduced training execution time by more than 90%
- End-to-end Retrieval-Augmented Generation system
- Automated ingestion and vectorization pipelines
- FastAPI, LangChain, and modern LLMs
- Production-ready deployment architecture
- CI/CD pipelines for machine learning workflows
- Model registry, monitoring, and deployment automation
- Kubernetes-native architecture
- Observability with Prometheus and monitoring tools
- PyTorch
- TensorFlow
- Scikit-Learn
- LangChain
- Hugging Face
- Time Series Forecasting
- Explainable AI
- PySpark
- Polars
- Pandas
- Kafka
- Distributed Data Processing
- MLflow
- Docker
- Kubernetes
- CI/CD
- Monitoring & Observability
- Azure Cloud
Published in Nature Scientific Data
https://www.nature.com/articles/s41597-024-03951-4
Published at BRACIS Conference
https://link.springer.com/chapter/10.1007/978-3-031-79035-5_12
- Production Machine Learning Systems
- MLOps & Platform Engineering
- Distributed ML Training
- Demand Forecasting
- LLM Applications & RAG
- AI Systems at Scale
💼 LinkedIn: https://linkedin.com/in/patrick-alves-0776921a7
📫 Email: tricksantos88@gmail.com
⭐ Feel free to explore my repositories and connect with me. I'm always interested in discussing Machine Learning, MLOps, Distributed Systems, and Production AI.