Cancel
Bilal Ayub is a Data Scientist at Seeloz in the United States with extensive experience in artificial intelligence and data analysis.
Company
Bilal Ayub is currently employed at Seeloz in the United States as a Data Scientist. His work at Seeloz involves implementing advanced data science techniques to optimize various processes.
Previous Employment at Afiniti
Bilal Ayub previously worked at Afiniti in Lahore, Pakistan. He held the position of Data Scientist - Artificial Intelligence in 2020 for a duration of 8 months. Prior to this, from 2017 to 2020, he served as a Data Analyst - Artificial Intelligence at Afiniti, where he honed his skills in data analysis and artificial intelligence applications.
Educational Background
Bilal Ayub holds a Master's degree in Data Science from the Information Technology University, which he achieved between 2020 and 2022. Prior to this, he earned a BS in Electrical Engineering with a focus on Power from Lahore University of Management Sciences (LUMS) from 2013 to 2017. He completed his A Levels in Physics, Chemistry, Biology, and Mathematics at BeaconHouse Defence Campus from 2010 to 2012, and his O Levels in Mathematics, Chemistry, Biology, and Physics at Ibne Sina College between 2008 and 2010.
Research and Teaching Roles at Lahore University of Management Sciences
In 2016, Bilal Ayub worked as a Research Assistant at Lahore University of Management Sciences (LUMS) for 2 months. He also served as a Teaching Assistant at LUMS for two separate 4-month terms, one in 2016 and another in 2015. These roles contributed to his background in academic and research environments.
Early Career Experience
From 2011 to 2013, Bilal Ayub worked as an Instructor at Smartprep in Lahore, Pakistan. Additionally, he completed an internship at Pak Elektron Limited in 2015, focusing on gaining practical industry experience.
Technical Contributions
Bilal Ayub has made significant technical contributions in his field. He implemented advanced procurement techniques based on deep reinforcement learning to optimize inventory management. He designed an MLOps pipeline using Azure Machine Learning to train multiple reinforcement learning models in parallel, and utilized RayLib and Gym for hyperparameter optimization. He derived and implemented a solution to ensure zero stockouts while minimizing inventory for supply chains. Furthermore, he built an interactive dashboard using Python Dash to compare the performance of multiple reinforcement learning models against traditional supply chain models.
