Aadam

• Developed a comprehensive pipeline to analyze the effects of neoadjuvant chemotherapy on pancreatic cancer, using spatial, single‑cell, and bulk RNA‑seq data for holistic insights. • Optimized ISCHIA algorithm by translating codebase from R to Julia, achieving a remarkable 1500x speedup in processing time and enhancing research efficiency. • Developed a pipeline for processing subcellular spatial RNA‑seq data (stereo‑seq), leveraging advanced deep learning methods to extract single‑cell level information, facilitating high‑resolution tissue analysis

• Designed and implemented a Python framework extending the Carla simulator by integrating a PGM model to simulate dynamic environments representing real‑world scenarios, particularly focusing on unpredictable elements such as pedestrian behavior and traffic patterns. • Engineered an innovative system of intelligent sensor towers within CARLA, leveraging multi‑modal sensor fusion techniques to provide comprehensive environmental data for autonomous vehicles. • Contributed to advancing autonomous driving research by providing a more realistic and challenging virtual testing environment, potentially accelerating the development and validation of self‑driving technologies.

• Worked as part of the data engineering team, focusing on optimizing data pipelines and ensuring the accuracy and efficiency of data flow. • Led large‑scale data conversions, transforming raw datasets into standardized formats using Talend, enhancing the reliability of the data for analytical purposes. • Collaborated closely with cross‑functional teams to address data inconsistencies and streamline ETL processes, significantly reducing data processing times. • Developed monitoring tools to track the health and performance of data pipelines, allowing for proactive maintenance and reduced downtime.