Amir Saeed

Amir K. Saeed brings a wealth of experience from his impactful career in the oil and gas sector, where he has played key roles at Baker Hughes. Currently serving as a Machine Learning Scientist at Baker Hughes, Amir’s journey began with a solid foundation in mechanical engineering, completing his undergraduate degree at The University of Texas at Austin, followed by a master’s in data science from Johns Hopkins University. His expertise covers a range of areas, including design and process engineering, data analysis, and model building. Amir’s project portfolio reflects his diverse contributions within the energy technology industry, encompassing additive manufacturing, turbomachinery, asset management, forecasting, modeling, and emissions control. Amir’s research interests have led him to explore intriguing domains like multimodal data fusion, reinforcement learning, and effective data visualization. In addition to his research work, he possesses practical skills in software development, proficiently working with Python, MATLAB, R, C++, Java, and Docker. In essence, Amir K. Saeed merges his mechanical engineering background with his data science proficiency, delivering significant contributions that have left a mark on the oil and gas industry. Grounded in academic excellence and practical innovation, Amir continues to drive advancements in his field.

Education History

• B.S., Mechanical Engineering, The University of Texas at Austin
• M.S., Data Science, Johns Hopkins University

Work Experience

Lead Machine Learning Scientist, Baker Hughes Company

Publications

Amir Saeed, Francisco Holguin, Jonathon Gabriel, Alhassan S. Yasin, Benjamin M. Rodriguez. (2023). Reinforcement Learning Application to Satellite Constellation Sensor Tasking, SPIE, SPIE Defense + Commercial Sensing Program, Orlando, FL, May, 2023.

Casey J. Richards, Nawal Valliani, Benjamin A. Johnson, Nelson Ka Ki Wong, Angelo Pennati, Amir K. Saeed, Benjamin M. Rodriguez. (2023). Multimodal Data Fusion using Signal/Image Processing Methods for Multi-Class Machine Learning, SPIE, SPIE Defense + Commercial Sensing Program, Orlando, FL, May, 2023.

Professional Organizations

SPIE