Riverside Research

• Design, develop, and implement automated V&V and T&E frameworks to assess the accuracy, performance, and operational readiness of remote sensing data products, AI/ML models, and vendor-delivered geospatial capabilities • Lead the technical evaluation of commercial and government remote sensing platforms, sensors (multispectral, hyperspectral, SAR, LiDAR), and associated data products against mission-specific requirements • Develop and maintain scalable, production-grade machine learning pipelines for geospatial applications including change detection, land cover classification, object detection, and environmental monitoring • Apply state-of-the-art AI/ML techniques — including deep learning, transfer learning, self-supervised learning, and large vision/language models — to automate remote sensing data exploitation and analysis workflows • Conduct rigorous uncertainty quantification, validation metric development, and statistical performance benchmarking across multi-source, multi-temporal geospatial datasets • Collaborate with program managers, government customers, and interdisciplinary engineering teams to translate operational requirements into validated technical solutions • Author technical reports, white papers, and briefings documenting methodology, V&V results, and performance findings for government sponsors

• Design, implement, and optimize FPGA logic using AMD/Xilinx toolchains (Vivado, Vitis, HLS) development in VHDL/Verilog • Integrate FPGA designs into larger systems, ensuring robust verification, documentation, and deployment across multiple platforms (Zynq, UltraScale+, Versal) • Develop innovative machine learning and computer vision solutions to analyze and exploit large, complex datasets from remote sensing phenomenology • Develop algorithms and associated software tools using C/C++/Python and associated machine learning libraries (PyTorch, LibTorch) • Train AI/ML models and tune their hyperparameters for a given dataset and algorithm objectives • Provide solutions for data collection and data linting that enable rapid, automated curation of training data • Keep up with the SoTA practices for AI/ML • Adhere to teams’ standards for reviewing source code, unit-testing, source code control, and documentation practices • Utilize Python PEP8 standards.