Felipe is a Senior Data Engineer and Machine Learning Engineer who designs, deploys, and scales sophisticated data solutions that empower strategic decision-making and drive business growth. He transforms raw data into actionable insights using a blend of advanced analytics, robust engineering practices, and scalable cloud infrastructure. Felipe is proficient in statistical analysis (descriptive, inferential, causal inference) and end-to-end pipeline development, designing, building, and implementing sophisticated data pipelines and enterprise-grade data processing, analytics, and reporting applications. With expertise in Python, Pandas, SciPy, Scikit-learn, PySpark, TensorFlow, and MLOps best practices (unit testing, integration testing, model monitoring, and API development with FastAPI/Flask), he maintains and enforces common conventions, standards, and technologies across database structures and applications to drive scalability and increase consistency.
Delivering data warehouse and ETL solutions as part of an Agile team using advanced ML techniques to improve performance and processes.
Helping build and improve infrastructure, application, and performance development and ensuring tight security including data encryption, security groups, and environment scanning.
Ensuring high-quality deliverables and implementing DevOps and security best practices in fast-paced environments.
Developing and maintaining web scraping scripts that support data pipelines using Python, SQL, MongoDB, Docker, and related technologies.
Integrating multiple data sources and understanding best practices for merging complex datasets.
Monitoring and troubleshooting API endpoints to ensure data accuracy, completeness, and reliability.
Understanding the full data lifecycle from extraction to data modeling and how the data is implemented into products or transformed to apply complex analysis using ML algorithms/AI models.
Contributing to optimization of data storage and retrieval processes.
Assisting the development and maintenance of data warehouse architecture.
Participating in code reviews, documentation, and knowledge sharing sessions.
Led the development team in automating and optimizing production-level data pipelines, including data fetching, parsing, cleaning, model inference, and scaling, ensuring efficient and reliable data processing workflows.
Contributed to the strategic planning and evolution of data pipelines, aligning technical solutions with business objectives to drive innovation and efficiency.
Implemented code optimizations and parallel processing techniques, reducing model inference time from 5 seconds to 0.8 seconds, significantly improving user experience and increasing retention rates by 15%.
Redesigned data pipeline architecture and established real-time monitoring, reducing failure rates by 40% and enhancing operational efficiency by 25%, enabling faster and more informed business decisions.
Collaborated with cross-functional teams to maintain and enhance the quality of Machine Learning components, delivering innovative credit scoring solutions in the DeFi sector.
Acted as the primary liaison between development, data science, and product management teams, effectively communicating progress and aligning expectations to ensure project success.
Guided and mentored junior team members, fostering professional growth and enhancing the team’s technical capabilities.
Organized internal workshops and training sessions, elevating the team’s proficiency in advanced Machine Learning techniques, leading to the successful deployment of three new models into production within six months.
Deployed new solutions to implement the game's balance model into production on AWS using MLOps best practices.
Worked on a probability model on the platform for sale of land (NFTs), increasing revenue generation for Illuvium.
Built and executed several data analysis pipelines to improve multiple game initiatives and functionalities.
Developed and managed end-to-end data pipelines to automate and scale business-critical analysis, integrating data from diverse sources for enhanced decision-making across game design and marketing strategy.
Created and deployed dynamic dashboards using Streamlit, providing stakeholders with real-time insights and enabling data-driven decisions that support game balance, user engagement, and monetization efforts.
Designed data models to empower decision-making in game development and marketing, delivering valuable business insights and identifying trends for targeted actions.
Led a team of engineers to manage and manipulate risk models to help the company maintain its sales channels.
Built new reputation models on AWS and transcribed notebooks into high-quality code per software best practices.
Developed and deployed data pipelines to handle the running of models using DAGs and ECS.
Determined catalog errors for identical products with differing descriptions, putting models into production using Docker and creating Airflow DAGs to schedule model updates.
Illuvium develops and publishes AAA play-to-earn crypto games, removing the ownership gap between gamers and games to create a community-governed collaborative game development model. It offers collectible NFT assets and in-game functionalities that are playable across multiple games within the Illuvium metaverse. Managed data analysis tasks, built new data pipelines for automated analysis, and deployed new data models to help with decision-making.
Olist is an SMB commerce enabler ecosystem providing end-to-end solutions for customers to sell online. Provided Data Science expertise to enhance data analytics and risk management, taking over several data initiatives with a product-oriented mindset to deliver solutions.