• Designed and implemented a real-time data pipeline to process semi-structured data by integrating 250 million raw records from 30+ data sources using Pyspark.• Designed an optimized data pipeline using Databricks, S3, and Azure, reducing data processing time by 30%. This enhancement enabled the DS team to achieve a 20% increase in decision-making efficiency.• Used PySpark to distribute data processing on large streaming datasets, improving ingestion and speed by 67%.• Utilized Scala to leverage its functional programming capabilities in optimizing data transformations and processing within the pipeline, resulting in a 15% reduction in code complexity and improved maintainability.• Integrated Natural Language Processing (NLP) tools like spaCy and NLTK for improved handling of unstructured text data, resulting in a 25% enhancement in data understanding.• Applied Reinforcement Learning algorithms to dynamically optimize resource allocation, reducing wastage by 20% and enhancing overall system efficiency.

• Applied SQL, PySpark, and Python to analyze sensor data from diverse aircraft systems, identifying patterns for strategic maintenance solutions and achieving a 20% reduction in operational disruptions.• Collaborated cross-functionally to implement data-driven aircraft solutions, reducing unscheduled maintenanceevents by 30%.• Led a team of data analysts in designing and implementing SQL-based solutions, optimizing maintenance schedules for Airbus A350, A320, Boeing 737, and 787, resulting in a $12,000 cost savings.• Led Apache Spark ETL projects, optimizing data workflows and integrating SQLServer. Implemented cloudnative applications with Java, utilizing GitLab-CI for seamless integration and fostering effective teamwork.

• Utilized SQL queries to extract and preprocess over 10,000 maintenance records from Airbus databases. Processed data using Pandas and NumPy, resulting in a 20% reduction in preprocessing time and ensuring data integrity.• Analyzed operational parameters and performance metrics of the A350 Nacelle Thrust Reverser, identifying critical trends and patterns. Generated visualizations using Matplotlib, facilitating data-driven decision-making processes.• Developed interactive dashboards and reports, resulting in a 30% increase in stakeholder engagement. Presented key findings to senior management, contributing to strategic planning and operational improvements.

Enhanced Predictive Maintenance Analysis for Aircraft ComponentsCollected and preprocessed maintenance data: Gathered historical maintenance records, cleaned the data, handled missing values, and ensured consistency for analysis.Developed predictive models and evaluated performance: Built machine learning models to predict maintenance needs, fine-tuned parameters for accuracy, and assessed model performance using evaluation metrics.Integrated solutions and deployed for real-time monitoring: Integrated predictive models into existing systems, ensured seamless data flow, and deployed for real-time monitoring of aircraft component health.Documented methodologies, created reports, and presented findings: Documented data preprocessing, model development, and integration processes. Created reports summarizing findings and presented them to stakeholders within Collins Aerospace.ce.