Abstract: The characterization of excited-state structure in semiconductor quantum dot (QD) devices is an important component of tuning them for spin-qubit operation. I will discuss two projects that focus on the characterization of excited states in QDs. First, I will present valley splitting measurements in a device with a quantum well containing an average of 5% Ge. We extract valley splitting and orbital splitting across two samples and four barrier-gate tuning configurations, and observe a positive correlation between the valley and orbital splittings. Random Ge-alloy disorder simulations reproduce the measured energy scale and are consistent with the interpretation that experimental tuning paths change how the dot samples the random alloy landscape. Next, I will present Spectroscopy With Intelligent Feature Tracking (SWIFT), a framework that combines machine-learning (ML)-assisted feature identification with physics-informed geometric processing to extract energy-level splittings from pulsed-gate spectroscopy data. Using Si/SiGe QD devices, we demonstrate SWIFT both offline and in real time, including automated tracking of QD excited states and lead resonances. These results provide a path toward incorporating confidence-guided excited-state spectroscopy into autonomous QD characterization, tuning, and optimization.