People — FloLink

Babak Akbari, PhD, PE

Babak is a technologist with diverse and deep experience in oil and gas drilling and well intervention field operations with various companies including Chevron, aerospace testing operations with SpaceX, and has also worked as a data scientist with Baker Hughes delivering predictive maintenance solutions using cutting edge machine-learning models. Babak has served in various volunteer capacities including the chair of SPE GCS Data Analytics for 2021-22 season leading a team of 20 volunteers, delivering over 10 events including the well-attended Data Science Convention and currently serves as the US Liaison of SPE WITS. He has delivered computer vision and AI solutions within oil and gas and aerospace, focusing on immediate value-adding and iterative improvement — bridging deep operational knowledge with practical machine-learning deployment.

Hamid Karami, PhD

Dr. Hamid Karami is an assistant professor at Mewbourne School of Petroleum and Geological Engineering of the University of Oklahoma, where he started in 2017. He received his BSc degree (2009) from Sharif University of Technology, and MSc (2011) and PhD (2015) degrees from the University of Tulsa, all in Petroleum Engineering. He worked as a research associate at Tulsa University Fluid Flow Projects (TUFFP), and Tulsa University Horizontal Well Artificial Lift Projects (TUHWALP), before joining OU. At OU, Dr. Karami has led several projects funded by ACS, QNRF, or sponsored by industrial entities, applying his knowledge of multiphase fluid dynamics and artificial lift. Since 2022, he has also worked as a part-time flow assurance consultant for Wood Group. His main teaching and research expertise areas are production engineering, multiphase flow, flow assurance, and artificial lift — domain knowledge that is essential for developing and validating AI and machine-learning models for production optimization and flow monitoring.

Alireza Pedram, PhD

Dr. Ali Reza Pedram is an Assistant Professor of Computer Science at the University of Oklahoma, specializing in robotics, computer vision, and AI methods for complex, real-world systems. His work focuses on developing data-efficient and robust vision-based methods for decision-making under uncertainty, with applications in autonomous systems, inspection, and large-scale monitoring. He has extensive experience in modern computer vision pipelines, including deep learning–based detection and segmentation models (e.g., YOLO), developed using frameworks such as PyTorch, TensorFlow, and OpenCV. His research, supported by agencies such as NASA, ONR, and DARPA, bridges advanced AI with practical deployment, enabling scalable and reliable vision-driven solutions in challenging industrial and operational environments.