Geraldine Castillo
Solution Engineer (Data & ML Integration)
Experience
Solution Engineer (Data & ML Integration)
Amadeus Data Processing GmbH
- Designed ML-ready data integration workflows between on-premise systems and cloud platforms (Snowflake, AWS Redshift, Azure), enabling scalable feature engineering and model deployment
- Implemented automated ML pipeline deployment using Python, SQL, and CI/CD tools, reducing model deployment time by 60%
- Developed data transformation logic for master data synchronization across ERP and analytics systems, ensuring data quality for predictive models
- Collaborated with cross-functional teams to translate business requirements into mathematical specifications for ML solutions
Senior Data Scientist & ML Engineer
IQ-EQ Global Investor Services
- Developed and validated predictive models for customer segmentation and revenue forecasting using ensemble methods (XGBoost, Random Forest), achieving 85% accuracy
- Applied advanced statistical modeling techniques (Bayesian inference, multivariate regression) to optimize pricing strategies, contributing to 12% revenue growth
- Operationalized ML models on Azure ML platform with automated retraining pipelines and monitoring dashboards
- Integrated ERP data with cloud analytics platforms, processing complex distributed data sources for feature generation
- Conducted hyperparameter tuning and cross-validation for model optimization, improving F1-score by 18%
Data Scientist & ML Specialist
Ernst and Young (EY)
- Developed production-ready ML models using TensorFlow and PyTorch for customer churn prediction, achieving 89% recall and reducing churn by 15%
- Applied semi-supervised learning techniques to leverage unlabeled data, improving model performance by 22% with limited labeled samples
- Implemented time series forecasting models (Prophet, ARIMA, LSTM) for demand prediction, achieving MAE improvement of 35% over baseline
- Designed and deployed scalable ML infrastructure on Snowflake + AWS, processing 10M+ customer interactions daily
- Performed advanced feature engineering including lag features, rolling statistics, and interaction terms, creating 50+ features from raw data
- Translated complex business optimization problems (budget allocation, campaign ROI) into mathematical formulations and implemented solutions
- Processed semi-structured data (JSON, logs) from multiple sources using PySpark for distributed processing and model training
Machine Learning Engineer
Infor
- Built and operationalized gradient boosting models (XGBoost, LightGBM) for customer lifetime value prediction, contributing to 10% revenue growth
- Developed end-to-end ML pipelines on AWS (SageMaker, S3) and Snowflake, including data preprocessing, model training, and automated deployment
- Applied ensemble learning methods combining multiple models to achieve 92% accuracy in fraud detection, reducing false positives by 40%
- Implemented A/B testing framework for model evaluation, measuring statistical significance and business impact of ML interventions
- Performed data wrangling on complex, distributed data sources (ERP, e-commerce, CRM) using Python and SQL
- Optimized hyperparameters using grid search and Bayesian optimization, reducing model training time by 50% while improving performance
Data Scientist
Ecorenew Group
- Developed time series forecasting models using ARIMA and Prophet, improving demand prediction accuracy by 25% for inventory optimization
- Built pricing optimization engine using regression models and constraint optimization, improving gross profitability by 10%
- Applied statistical analysis and hypothesis testing to identify revenue drivers and operational bottlenecks
- Integrated e-commerce data with analytics systems for real-time sales and product performance tracking
Industries Experience
See where this freelancer has spent most of their professional time. Longer bars indicate deeper hands-on experience, while shorter ones reflect targeted or project-based work.
Experienced in Information Technology (3.5 years), Professional Services (2 years), Tourism (1 year), Retail (1 year), and Banking and Finance (0.5 years).
Business Areas Experience
The graph below provides a cumulative view of the freelancer's experience across multiple business areas, calculated from completed and active engagements. It highlights the areas where the freelancer has most frequently contributed to planning, execution, and delivery of business outcomes.
Experienced in Business Intelligence (7 years), Information Technology (3 years), Supply Chain Management (1 year), and Finance (0.5 years).
Summary
Data Scientist with 5+ years of experience developing and operationalizing machine learning models to solve complex business problems. Expertise in statistical modeling, deep learning, and cloud-based ML platforms (AWS, Azure, GCP). Proven track record in translating business requirements into mathematical optimization problems and deploying production-ready ML solutions. Specialized in feature engineering, ensemble methods, and Foundation Models (LLMs) integration. Published researcher in AI applications with strong foundation in Python, TensorFlow, and distributed ML systems.
Skills
- Machine Learning & Deep Learning: Xgboost, Random Forest, Gradient Boosting, Neural Networks, Tensorflow, Pytorch, Ensemble Learning
- Statistical Modeling: Bayesian Inference, Multivariate Statistics, Time Series Analysis, Hypothesis Testing, A/b Testing
- Advanced Ml Algorithms: Semi-supervised Learning, Reinforcement Learning, Causal Inference, Synthetic Data Generation
- Cloud Ml Platforms: Aws (Sagemaker, S3, Redshift), Microsoft Azure (Ml Studio, Data Lake), Google Cloud (Vertex Ai, Bigquery)
- Ml Operations & Deployment: Model Versioning, Hyperparameter Tuning, Cross-validation, Ci/cd For Ml, Apache Airflow
- Programming & Tools: Python (Pandas, Numpy, Scikit-learn), R, Pyspark, Sql, Dbt, Git
- Foundation Models & Genai: Llm Integration, Transformer Models, Fine-tuning, Prompt Engineering, Rag Architecture
- Data Engineering: Complex Data Wrangling, Distributed Data Processing, Feature Engineering, Data Pipelines
Languages
Education
Technische Hochschule Deggendorf
M.Eng. · Applied AI for Digital Production Management · Deggendorf, Germany
Mapua University
M.Sc., Specialization: Advanced Machine Learning, Statistical Modeling, Deep Learning, Time Series Analysis · Business Analytics · Philippines · 1.3 - Excellent
Polytechnic University of the Philippines
B.Sc. · Industrial Engineering · Philippines · 1.9 - Very Good
Profile
Frequently asked questions
Do you have questions? Here you can find further information.
Where is Geraldine based?
What languages does Geraldine speak?
How many years of experience does Geraldine have?
What roles would Geraldine be best suited for?
What is Geraldine's latest experience?
What companies has Geraldine worked for in recent years?
Which industries is Geraldine most experienced in?
Which business areas is Geraldine most experienced in?
Which industries has Geraldine worked in recently?
Which business areas has Geraldine worked in recently?
What is Geraldine's education?
What is the availability of Geraldine?
What is the rate of Geraldine?
How to hire Geraldine?
Average rates for similar positions
Rates are based on recent contracts and do not include FRATCH margin.
Similar Freelancers
Discover other experts with similar qualifications and experience
Experts recently working on similar projects
Freelancers with hands-on experience in comparable project as a Solution Engineer (Data & ML Integration)
Nearby freelancers
Professionals working in or nearby Regensburg, Germany