Muhammad Ali

Built an AI system that optimizes heating and cooling in smart buildings in real-time, cutting energy costs and improving comfort level using reinforcement learning It runs on AWS, with IoT Core handling sensor streams, SageMaker training the AI models, and QuickSight giving clear visibility. 1. Designed and deployed robust ETL pipelines on AWS 2. Implemented reinforcement learning algorithms, to optimize energy consumption 3. User-friendly frontends to analyze historical data and interact with ML models

1. Designed and implemented an ETL pipeline for collecting and storing building IOT sensor data. 2. Developed interactive dashboard to monitor and analyze real-time data. 3. Managed relational databases, ensuring scalability and efficient handling of multi-building data. 4. Built time-series forecasting models to predict energy consumption and occupancy in buildings. 5. Automated data cleaning and preprocessing workflows, improving model accuracy.

1. Designed and implemented ETL pipeline for high-frequency PV and transformer data. 2. Managed and optimized data warehouses, enabling real-time analytics and reporting. 3. Built and deployed forecasting models for solar energy production, reducing reliance on fossil fuels for electricity generation. 4. Automated data ingestion and transformation workflows to improve pipeline efficiency. 5. Collaborated with cross-functional team to ensure data quality, consistency, and scalability.

Machine Learning & AI, AWS, Cloud Computing, Databases, ETL Pipelines