About
Rodrigo Yepez-Lopez is a Machine Learning Engineer with an M.S. and B.S. in Computer Science and over four years of experience building data- and compute-intensive ML systems. He has worked in several areas including education, healthcare, climate science, and high-performance computing. Working on the full ML pipeline, multimodal model development (audio, text, and image) and deployment with real-time processing, monitoring and retraining. He has led core components such as data infrastructure and modeling workflows in both independent and team settings, delivering measurable improvements in predictive accuracy documented through four peer-reviewed IEEE publications and deployed research systems. His technical stack includes Python, SQL, PyTorch, TensorFlow, Spark, Docker, Linux, AWS, and modern LLM workflows such as LoRA/PEFT fine-tuning and retrieval-augmented generation (RAG). U.S. Citizen.
What I Do
- Data ingestion, pipelines, and large-scale database systems designed to integrate complex, multi-source data and support reliable downstream analysis
- Analytics and machine learning workflows that move from exploration to validated models for structured and unstructured data
- Production ML pipelines designed with deployment, monitoring, drift detection, and retraining in mind from the outset
- Real-time processing, visualization, and alerting systems that enable timely insight and operational response
- Reproducible, maintainable software systems that support sustained accuracy, reliability, and data-driven decision making
Technical Skills
| Area | Skill |
|---|---|
| CS & Software Engineering | Python, SQL, C++, Linux, Git, Docker |
| Data Systems & Infrastructure | Large-scale databases, PySpark, AWS, HPC/SLURM |
| Analytics & Modeling | Statistical modeling, time-series analysis, data visualization |
| Machine Learning | PyTorch, Keras, Scikit-Learn, deep learning, multimodal models |
My technical background applies to data-intensive environments such as enterprise analytics, technology, and research—where scalable systems and reliable analytics are critical.