Senior AI Software Engineer /Data Scientist • PhD in Artificial Intelligence
Pioneering innovative AI solutions and advancing the future of artificial intelligence through research and engineering excellence.
Get In TouchWith a doctoral degree in Artificial Intelligence and extensive experience as a Senior AI Software Engineer, I specialize in developing cutting-edge AI systems that solve complex real-world problems.
My expertise spans machine learning, deep learning, natural language processing, computer vision, signal processing, and UAV communications. I'm passionate about translating theoretical AI research into practical applications that drive innovation and create value. Regarding specific skills, I have a strong background in Python, TensorFlow, and PyTorch, Docker, Azure Pipelines, Azure Machine Learning, and more.
I thrive on tackling challenging problems and collaborating with cross-functional teams to deliver AI solutions that exceed expectations.
Drive end-to-end AI and data science initiatives for oil & gas operations, from data cleaning and predictive modeling to deploying scalable ML/AI systems in production. Architect and implement RAG and database-powered chatbots, advanced NLP models, and real-time analytics pipelines, leveraging Azure cloud infrastructure to deliver actionable insights and optimize drilling and well operations.
Dissertation: 'Spectrum Surveying for Machine Learning-Assisted UAV Communications' - Research focused on machine learning applications in UAV communications.
Led the R&D unit to promote research and innovation in engineering education.
Worked as a Program Coordinator and Lecturer for students of Bachelor in Computer Engineering and Electronics & Communication Engineering.
Research focused on machine learning applications in UAV communications.
Specialized in Machine Learning and Data Science with focus on artificial intelligence applications and cloud computing.
Foundation in electronics, computer science, programming, and engineering principles with focus on communications systems.
Developed fully convolutional DNN models using TensorFlow to reconstruct a radio map as an image and provide an uncertainty metric given the partial pixels. Implemented a dynamic approach-based routing algorithm to find the optimal path based on an uncertainty metric provided by DNN models.
This paper investigates radio map estimation (RME) using real-world data collected using a custom-built UAV and Software defined radio (SDR)-based embedded system, moving beyond synthetic evaluations. It systematically compares classical and deep learning-based methods, analyzing their accuracy, complexity, and trade-offs. Additionally, it introduces an enhancement to improve deep learning approaches and releases datasets and tools to support further scientific research in practical RME.
This paper proposes an efficient algorithm for placing UAV-mounted aerial base stations (ABSs) using radio maps to model realistic air-to-ground channels. The method ensures coverage, respects backhaul and no-fly constraints, and scales linearly with the number of users. Simulations confirm its superior performance compared to conventional approaches.
This work studies the fundamentals of radio map estimation (RME), which predicts signal strength across a region from limited measurements. It quantifies the complexity of radio maps, establishes error bounds for common interpolation methods, and introduces the proximity coefficient to characterize RME difficulty. Numerical experiments validate the theoretical results in realistic environments
