Senior Python Engineer | Data Engineering | MLOps | ADAS and HIL Automation
Based in Brazil. Open to remote opportunities.
I build data-driven engineering systems with Python, machine learning, optimization, and simulation workflows. My experience is strongest in automotive validation environments, especially ADAS, SIL, and HIL workflows, where I develop tools for data processing, test automation, model evaluation, and engineering analytics.
I focus on practical systems: maintainable Python code, reproducible pipelines, automated validation, clear architecture, and tools that engineering teams can use in real workflows.
- Python data pipelines for simulation, validation, analytics, and reporting
- ETL-style workflows for MF4, CSV, JSON, and engineering measurement data
- Machine learning workflows for optimization, model evaluation, and surrogate modeling
- Automated validation pipelines using Pytest, CI/CD, and reproducible tooling
- Internal dashboards and tools for engineering and data workflows
- Simulation-based optimization using Bayesian Optimization and Genetic Algorithms
Data-driven calibration tooling using Genetic Algorithms and real engineering data. The project supports ADAS calibration workflows and is connected to published work on AI-assisted ADAS development.
Tech: Python, PyGAD, optimization, validation workflows
Bayesian Optimization framework for simulation-based systems. It compares optimization strategies against parameter sweeping, builds Gaussian Process surrogate models, generates Pareto front analysis, and exports experiment results for engineering evaluation.
Tech: Python, NumPy, SciPy, scikit-learn, Gaussian Processes, Matplotlib
Streamlit dashboard for evaluating and comparing regression models from CSV prediction data. It supports model comparison, residual analysis, prediction distributions, error patterns, automated tests, and Docker-based execution.
Tech: Python, Streamlit, Pandas, NumPy, scikit-learn, Matplotlib, Seaborn, Docker, Pytest
Computer vision project focused on face recognition scenarios with masked faces.
Tech: TensorFlow, Keras, NumPy
Data visualization tools for engineering analysis and reporting.
Tech: Python, data visualization, engineering analytics
- Languages: Python, SQL, JavaScript / TypeScript, C++
- Data Engineering: ETL-style pipelines, data processing, validation, reporting, CSV / JSON / XLSX workflows
- Python Ecosystem: Pandas, NumPy, SciPy, scikit-learn, Streamlit, Pytest
- Machine Learning: Bayesian Optimization, Genetic Algorithms, Gaussian Processes, model evaluation
- Backend and Applications: Flask, FastAPI, REST APIs, desktop tooling, dashboards
- DevOps and Quality: Docker, Git, CI/CD pipelines, automated tests
- Engineering Data: MF4 / asammdf, CarMaker, Simulink, SIL / HIL validation workflows
- Using AI-Based Data Algorithm to Support ADAS Development
- Efficient Multi-Objective Optimization of AEB Systems
- Email: ygorgalbierlopes@gmail.com
- LinkedIn: https://www.linkedin.com/in/ygor-galbier/