Software Between Quantum and Machine Learning - and Down to Pulses

Contemporary quantum computing platforms remain, in essence, programmable physical systems whose control is typically mediated through unitary gate abstractions. While such abstractions provide a uniform interface, they obscure important aspects of the underlying hardware and may limit the exploitation of its full capabilities. Direct operation at the level of control pulses offers a more expressive and physically faithful paradigm, enabling, for instance, the implementation of tailored error-mitigation and optimisation strategies. However, this increased expressivity comes at the cost of greater complexity from the perspective of quantum software development, necessitating structured and accessible tooling. We present a software framework, integrated within the QML-Essentials package, that extends quantum machine learning (QML) methodologies to encompass pulse-level modelling. By embedding quantum optimal control (QOC) techniques within a QML setting, our approach enables the seamless combination of gate-based and pulse-level representations in a unified modelling paradigm. The framework provides a comprehensive suite of modelling and analytical capabilities. ... mehrIn particular, we introduce composable ansatz constructions based on interchangeable building blocks, alongside support for end-toend optimisation of pulse parameters. Motivated by the central role of quantum Fourier models (QFMs), we further incorporate a range of Fourier-analytic diagnostics, including the Fourier fingerprint and the Fourier coefficient correlation (FCC), complemented by extended measures of entanglement. All performancecritical components are implemented in a high-performance environment using JAX and supported by a dedicated quantum simulator. Taken together, the framework facilitates reproducible and systematic investigations in QML research, while bridging the conceptual and practical divide between abstract circuitbased models and hardware-aware pulse-level optimisation. It provides a robust foundation for future developments at the intersection of quantum machine learning and quantum control.